{"as_of":"2026-08-15T18:01:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:a2409457f46c737b5109b7cf5a886cdce90764b26845a81ac658c243256fb9e9","coverage":[{"denominator":65,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":65,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T11:29:49.140988Z","state":"measured"},{"denominator":71,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":71,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-15T06:32:42.880941+00:00","state":"measured"},{"denominator":6,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":6,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-15T14:57:06.882841Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"arxiv_reference","source_observed_at":"2026-05-13T01:47:04.386257Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2506.02362","last_updated":"2025-06-03T01:37:09Z","snapshot_observed_at":"2026-08-13T05:58:16.125055Z","submitted_at":"2025-06-03T01:37:09Z","title":"MISLEADER: Defending against Model Extraction with Ensembles of Distilled Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2506.02362","snapshot_observed_at":"2026-08-06T22:23:07.680268Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2506.22521","last_updated":"2025-06-26T22:02:01Z","snapshot_observed_at":"2026-08-07T22:00:37.560675Z","submitted_at":"2025-06-26T22:02:01Z","title":"A Survey on Model Extraction Attacks and Defenses for Large Language Models","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-06T22:23:07.680268Z"},"links":{"cited_paper":"/paper/2506.02362","citing_paper":"/paper/2506.22521"},"observation_digest":"sha256:4b749f6f8b293e9d5ae2ac01a1eee3c7c1b65ae5a9fa854d882da45512468f24","observation_id":"2915912e-4524-4069-9543-c9c1df610d22","resolution":{"observed_at":"2026-08-06T22:23:07.680268Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2506.02362","last_updated":"2025-06-03T01:37:09Z","snapshot_observed_at":"2026-08-13T05:58:16.125055Z","submitted_at":"2025-06-03T01:37:09Z","title":"MISLEADER: Defending against Model Extraction with Ensembles of Distilled Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2506.02362","snapshot_observed_at":"2026-08-05T18:12:37.034350Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2508.15031","last_updated":"2025-08-27T05:10:26Z","snapshot_observed_at":"2026-08-14T23:52:31.572833Z","submitted_at":"2025-08-20T19:49:59Z","title":"A Systematic Survey of Model Extraction Attacks and Defenses: State-of-the-Art and Perspectives","version":2},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-05T18:12:37.034350Z"},"links":{"cited_paper":"/paper/2506.02362","citing_paper":"/paper/2508.15031"},"observation_digest":"sha256:9404b8684cc9f68abcc29be4d60988b6a53737a7fa388fcc02f2fc681b6301a7","observation_id":"ca490b50-3be2-4d14-98ef-3e15920dd554","resolution":{"observed_at":"2026-08-05T18:12:37.034350Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2506.02362","last_updated":"2025-06-03T01:37:09Z","snapshot_observed_at":"2026-08-13T05:58:16.125055Z","submitted_at":"2025-06-03T01:37:09Z","title":"MISLEADER: Defending against Model Extraction with Ensembles of Distilled Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2506.02362","snapshot_observed_at":"2026-08-05T15:39:56.130610Z","title":"Misleader: Defending against model extraction with ensembles of distilled models,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2508.19641","last_updated":"2025-08-27T07:37:52Z","snapshot_observed_at":"2026-08-08T08:19:58.466694Z","submitted_at":"2025-08-27T07:37:52Z","title":"Intellectual Property in Graph-Based Machine Learning as a Service: Attacks and Defenses","version":1},"reference_index":182,"source":"pdf_text","source_observed_at":"2026-08-05T15:39:56.130610Z"},"links":{"cited_paper":"/paper/2506.02362","citing_paper":"/paper/2508.19641"},"observation_digest":"sha256:3a3f0b3363b273aa27b76178f8654c56ab3a6b5c96c5561fef753a090fdbc0c8","observation_id":"5da6b5f7-7453-4261-b633-fd1d64dc03b0","resolution":{"observed_at":"2026-08-05T15:39:56.130610Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2506.02362","last_updated":"2025-06-03T01:37:09Z","snapshot_observed_at":"2026-08-13T05:58:16.125055Z","submitted_at":"2025-06-03T01:37:09Z","title":"MISLEADER: Defending against Model Extraction with Ensembles of Distilled Models","version":1},"cited_work":{"arxiv_id":"2506.02362","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2506.02362","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Misleader: Defending against model extraction with ensembles of distilled models","venue":null,"work_id":"d88b0632-6089-4e74-92d5-591745a63c52","year":2025},"citing_paper":{"arxiv_id":"2605.11301","last_updated":"2026-05-11T22:42:12Z","snapshot_observed_at":"2026-08-15T01:08:53.505050Z","submitted_at":"2026-05-11T22:42:12Z","title":"LatentRouter: Can We Choose the Right Multimodal Model Before Seeing Its Answer?","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-05-13T01:42:54.802658Z"},"links":{"cited_paper":"/paper/2506.02362","citing_paper":"/paper/2605.11301"},"observation_digest":"sha256:d27ef1d8d79f12578bcf29783d46430cb64cda3430901d40049f3e5f7b926c5e","observation_id":"beefe17b-0f1a-4e24-8930-e80ff25bc258","resolution":{"observed_at":"2026-05-13T01:47:04.388649Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2506.02362","last_updated":"2025-06-03T01:37:09Z","snapshot_observed_at":"2026-08-13T05:58:16.125055Z","submitted_at":"2025-06-03T01:37:09Z","title":"MISLEADER: Defending against Model Extraction with Ensembles of Distilled Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2506.02362","snapshot_observed_at":"2026-08-01T23:20:43.484131Z","title":"Misleader: Defending against model extraction with ensembles of distilled models,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.15467","last_updated":"2026-07-16T21:33:37Z","snapshot_observed_at":"2026-08-11T09:00:14.024891Z","submitted_at":"2026-07-16T21:33:37Z","title":"ADS-C: Antidistillation Sampling for Classification","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-01T23:20:43.484131Z"},"links":{"cited_paper":"/paper/2506.02362","citing_paper":"/paper/2607.15467"},"observation_digest":"sha256:1ef20cfe5aee5903149b53a3ed1b0a238b9a6326f4832e7cf02b5bd46a899af8","observation_id":"9dde8944-2c60-4c02-844d-c0fd23468225","resolution":{"observed_at":"2026-08-01T23:20:43.484131Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2506.02362","last_updated":"2025-06-03T01:37:09Z","snapshot_observed_at":"2026-08-13T05:58:16.125055Z","submitted_at":"2025-06-03T01:37:09Z","title":"MISLEADER: Defending against Model Extraction with Ensembles of Distilled Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2506.02362","snapshot_observed_at":"2026-08-15T14:57:06.882841Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2608.03087","last_updated":"2026-08-04T04:00:10Z","snapshot_observed_at":"2026-08-15T14:50:42.658980Z","submitted_at":"2026-08-04T04:00:10Z","title":"SynEnergy: Anomaly Semantic-Guided Diffusion for Synthetic Energy Data Generation","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-15T14:57:06.882841Z"},"links":{"cited_paper":"/paper/2506.02362","citing_paper":"/paper/2608.03087"},"observation_digest":"sha256:cee4669c5451311a8e50831052d1f25946249f8c8d9ced7bbbde20faf2115bd2","observation_id":"9748fb04-fdae-4f6d-8361-e4a3c70caed8","resolution":{"observed_at":"2026-08-15T14:57:06.882841Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2506.02362/citation-record","integrity":"/paper/2506.02362/integrity","json":"/paper/2506.02362/citation-record.json","paper":"/paper/2506.02362"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T11:29:55.378187Z","title":"Turning your weakness into a strength: Watermarking deep neural networks by backdooring","venue":null,"work_id":"c15f8a00-dac9-4b3e-8f84-0a219ba3a69c","year":2018},"citing_paper":{"arxiv_id":"2506.02362","last_updated":"2025-06-03T01:37:09Z","snapshot_observed_at":"2026-08-13T05:58:16.125055Z","submitted_at":"2025-06-03T01:37:09Z","title":"MISLEADER: Defending against Model Extraction with Ensembles of Distilled Models","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-07T11:29:42.954810Z"},"links":{"citing_paper":"/paper/2506.02362"},"observation_digest":"sha256:15af898102ac4b793ee83e06d7d9eb611934d75cba95597ad13e1e5c6c96e885","observation_id":"96c75794-e6be-4f5f-ab25-f440b4922437","resolution":{"observed_at":"2026-08-07T11:29:55.383335Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T11:29:55.361487Z","title":"Backpropagation and stochastic gradient descent method.Neurocomputing, 5(4-5):185–196, 1993","venue":null,"work_id":"d0423e82-e9fb-415f-8a59-5f3ce77ac0f5","year":1993},"citing_paper":{"arxiv_id":"2506.02362","last_updated":"2025-06-03T01:37:09Z","snapshot_observed_at":"2026-08-13T05:58:16.125055Z","submitted_at":"2025-06-03T01:37:09Z","title":"MISLEADER: Defending against Model Extraction with Ensembles of Distilled Models","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-07T11:29:43.005028Z"},"links":{"citing_paper":"/paper/2506.02362"},"observation_digest":"sha256:2d54cd806dc099b04802fcf569db64f9442f7f7318ab13e7791aa51f5739689f","observation_id":"be2e1a90-1d5f-4fd9-9a63-0f39a787d654","resolution":{"observed_at":"2026-08-07T11:29:55.367144Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T11:29:43.068897Z","title":"Knowledge distillation: A good teacher is patient and consistent","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.02362","last_updated":"2025-06-03T01:37:09Z","snapshot_observed_at":"2026-08-13T05:58:16.125055Z","submitted_at":"2025-06-03T01:37:09Z","title":"MISLEADER: Defending against Model Extraction with Ensembles of Distilled Models","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-07T11:29:43.068897Z"},"links":{"citing_paper":"/paper/2506.02362"},"observation_digest":"sha256:9798fbc700fa0cdc73f981b70415b80338f792b7af77cfaed5d5e8daba34f6db","observation_id":"4bf8f852-8f14-4a77-b99b-b19f53f8c588","resolution":{"observed_at":"2026-08-07T11:29:43.068897Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T11:29:55.336044Z","title":"Data sharing and interoperability: Fostering in- novation and competition through apis.Computer Law & Security Review, 35(5):105314, 2019","venue":null,"work_id":"98951afc-512c-487e-a9f0-ced6321de618","year":2019},"citing_paper":{"arxiv_id":"2506.02362","last_updated":"2025-06-03T01:37:09Z","snapshot_observed_at":"2026-08-13T05:58:16.125055Z","submitted_at":"2025-06-03T01:37:09Z","title":"MISLEADER: Defending against Model Extraction with Ensembles of Distilled Models","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-07T11:29:43.149923Z"},"links":{"citing_paper":"/paper/2506.02362"},"observation_digest":"sha256:730ba85d401ef22dd6af37cc0292061311af29bd9b85d07ebabd4a7f5aff1f3a","observation_id":"8a5c073c-aa9a-4c3e-9684-cd0e2b2b7c20","resolution":{"observed_at":"2026-08-07T11:29:55.341246Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2503.16693","last_updated":"2025-03-20T20:25:32Z","snapshot_observed_at":"2026-08-14T13:34:42.073533Z","submitted_at":"2025-03-20T20:25:32Z","title":"ATOM: A Framework of Detecting Query-Based Model Extraction Attacks for Graph Neural Networks","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2503.16693","snapshot_observed_at":"2026-08-07T11:29:43.246771Z","title":"Atom: A framework of detecting query-based model extraction attacks for graph neural networks.arXiv preprint arXiv:2503.16693, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2506.02362","last_updated":"2025-06-03T01:37:09Z","snapshot_observed_at":"2026-08-13T05:58:16.125055Z","submitted_at":"2025-06-03T01:37:09Z","title":"MISLEADER: Defending against Model Extraction with Ensembles of Distilled Models","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-07T11:29:43.246771Z"},"links":{"cited_paper":"/paper/2503.16693","citing_paper":"/paper/2506.02362"},"observation_digest":"sha256:a4a10b827fac3f90ab190e7d508dfa46c869268b8f4147e06eb3ff95da237506","observation_id":"a3d4e200-4019-494e-8d89-8ced57857a80","resolution":{"observed_at":"2026-08-07T11:29:43.246771Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T11:29:43.346168Z","title":"The mnist database of handwritten digit images for machine learning research [best of the web].IEEE signal processing magazine, 29(6):141–142, 2012","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2506.02362","last_updated":"2025-06-03T01:37:09Z","snapshot_observed_at":"2026-08-13T05:58:16.125055Z","submitted_at":"2025-06-03T01:37:09Z","title":"MISLEADER: Defending against Model Extraction with Ensembles of Distilled Models","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-07T11:29:43.346168Z"},"links":{"citing_paper":"/paper/2506.02362"},"observation_digest":"sha256:08a6b86a116757427f4675d809782f96f85af179fe882e730088c8e5828bb082","observation_id":"0ea5740c-d6ed-43a8-9d60-590fb24db916","resolution":{"observed_at":"2026-08-07T11:29:43.346168Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T11:29:55.308474Z","title":"Simon and Schuster, 2024","venue":null,"work_id":"ffb12459-0592-46c0-86b0-45cd2621a6f6","year":2024},"citing_paper":{"arxiv_id":"2506.02362","last_updated":"2025-06-03T01:37:09Z","snapshot_observed_at":"2026-08-13T05:58:16.125055Z","submitted_at":"2025-06-03T01:37:09Z","title":"MISLEADER: Defending against Model Extraction with Ensembles of Distilled Models","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-07T11:29:43.393700Z"},"links":{"citing_paper":"/paper/2506.02362"},"observation_digest":"sha256:5e943ee65d723616445900691e97c56cd54491f375c4f0a56ef882c1a3945356","observation_id":"8bde58b8-d2d0-4209-9809-52ee97f3304c","resolution":{"observed_at":"2026-08-07T11:29:55.314420Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T11:29:55.291134Z","title":"An optimized intelligent open-source mlaas framework for user-friendly clustering and anomaly detection.The Journal of Supercomputing, 80(18):26658–26684, 2024","venue":null,"work_id":"a3723f63-88a8-4760-994b-6b18e48b1cdf","year":2024},"citing_paper":{"arxiv_id":"2506.02362","last_updated":"2025-06-03T01:37:09Z","snapshot_observed_at":"2026-08-13T05:58:16.125055Z","submitted_at":"2025-06-03T01:37:09Z","title":"MISLEADER: Defending against Model Extraction with Ensembles of Distilled Models","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-07T11:29:43.442394Z"},"links":{"citing_paper":"/paper/2506.02362"},"observation_digest":"sha256:1df314ebf8cb5f0c3f70353d60e8274526878628e609a3db525c5c0c0c24a374","observation_id":"41cd6786-0211-476e-93c5-9e4226f9f477","resolution":{"observed_at":"2026-08-07T11:29:55.296348Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T11:29:55.274652Z","title":"Efficient knowledge distillation from an ensemble of teachers","venue":null,"work_id":"79342df6-4153-4e31-ad6a-78f1b21c03ad","year":2017},"citing_paper":{"arxiv_id":"2506.02362","last_updated":"2025-06-03T01:37:09Z","snapshot_observed_at":"2026-08-13T05:58:16.125055Z","submitted_at":"2025-06-03T01:37:09Z","title":"MISLEADER: Defending against Model Extraction with Ensembles of Distilled Models","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-07T11:29:43.508645Z"},"links":{"citing_paper":"/paper/2506.02362"},"observation_digest":"sha256:ee516afab009675e6c43b110ba5cb5a491cdb2f1fc1594afb9de75ec6bedf1f4","observation_id":"fc6d3599-e8f9-4b43-985f-8551e58340d4","resolution":{"observed_at":"2026-08-07T11:29:55.280408Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T11:29:55.258117Z","title":"Model extraction attacks and defenses on cloud-based machine learning models.IEEE Communications Magazine, 58(12):83–89, 2021","venue":null,"work_id":"35cba0d4-edca-4a2b-bb0f-b051d5162c12","year":2021},"citing_paper":{"arxiv_id":"2506.02362","last_updated":"2025-06-03T01:37:09Z","snapshot_observed_at":"2026-08-13T05:58:16.125055Z","submitted_at":"2025-06-03T01:37:09Z","title":"MISLEADER: Defending against Model Extraction with Ensembles of Distilled Models","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-07T11:29:43.600457Z"},"links":{"citing_paper":"/paper/2506.02362"},"observation_digest":"sha256:f28fb73e825ecb5f0f4648e9830458f485484a3677acc763c80410334c658d5f","observation_id":"08e040c4-6dc7-4d73-9c5b-57430b1014a3","resolution":{"observed_at":"2026-08-07T11:29:55.263164Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T11:29:55.241573Z","title":"Machine learning as a service (mlaas)—an enterprise perspective","venue":null,"work_id":"40e4da5c-5ee3-4498-ab73-7b27628c7f7e","year":2022},"citing_paper":{"arxiv_id":"2506.02362","last_updated":"2025-06-03T01:37:09Z","snapshot_observed_at":"2026-08-13T05:58:16.125055Z","submitted_at":"2025-06-03T01:37:09Z","title":"MISLEADER: Defending against Model Extraction with Ensembles of Distilled Models","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-07T11:29:43.671344Z"},"links":{"citing_paper":"/paper/2506.02362"},"observation_digest":"sha256:9255ef5853e97ef74c6abf9e5a7f56bf908184cdc71e20295062ce87f9324d48","observation_id":"f16855de-899f-425e-8ec3-eda7369586a2","resolution":{"observed_at":"2026-08-07T11:29:55.246872Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T11:29:55.224204Z","title":"A realistic model extraction attack against graph neural networks.Knowledge-Based Systems, 300:112144, 2024","venue":null,"work_id":"2e626c9d-c029-4788-b17a-2f3ed104ddc1","year":2024},"citing_paper":{"arxiv_id":"2506.02362","last_updated":"2025-06-03T01:37:09Z","snapshot_observed_at":"2026-08-13T05:58:16.125055Z","submitted_at":"2025-06-03T01:37:09Z","title":"MISLEADER: Defending against Model Extraction with Ensembles of Distilled Models","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-07T11:29:43.747845Z"},"links":{"citing_paper":"/paper/2506.02362"},"observation_digest":"sha256:23980ce9fdd5ff36bbb1f4373724305c4410ea6597daa51669821ed2a0d0a1f1","observation_id":"6092f782-cd91-4955-acd6-94fdf7de893d","resolution":{"observed_at":"2026-08-07T11:29:55.230260Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"2412.16114","doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T11:29:49.495976Z","title":"The content moderator’s dilemma: Removal of toxic content and distortions to online discourse.arXiv preprint arXiv:2412.16114, 2024","venue":null,"work_id":"b7b4c685-7531-4d26-89f2-c0eec3d10bf5","year":2024},"citing_paper":{"arxiv_id":"2506.02362","last_updated":"2025-06-03T01:37:09Z","snapshot_observed_at":"2026-08-13T05:58:16.125055Z","submitted_at":"2025-06-03T01:37:09Z","title":"MISLEADER: Defending against Model Extraction with Ensembles of Distilled Models","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-07T11:29:43.823410Z"},"links":{"citing_paper":"/paper/2506.02362"},"observation_digest":"sha256:6bf54a9294df61c96e627d621265c8c6f9bd6493b17c3fe5dfc232001b0bc3dc","observation_id":"191e257e-35d0-42db-89c6-516d0d3adc49","resolution":{"observed_at":"2026-08-07T11:29:49.617476Z","resolver_source":"raw_fallback","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T11:29:43.878264Z","title":"Deep residual learning for image recognition","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2506.02362","last_updated":"2025-06-03T01:37:09Z","snapshot_observed_at":"2026-08-13T05:58:16.125055Z","submitted_at":"2025-06-03T01:37:09Z","title":"MISLEADER: Defending against Model Extraction with Ensembles of Distilled Models","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-07T11:29:43.878264Z"},"links":{"citing_paper":"/paper/2506.02362"},"observation_digest":"sha256:b9668e27aeb70554b1d3aeace9785cdbcfcd3a9b7c3e096fd90ba6d193efdf06","observation_id":"bea71f1e-f0d2-4ac2-ba6b-2269554dde38","resolution":{"observed_at":"2026-08-07T11:29:43.878264Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T11:29:55.197016Z","title":"Protecting intellectual property of language generation apis with lexical watermark","venue":null,"work_id":"75a544dd-914e-4dff-9d85-4b6fe374195e","year":2022},"citing_paper":{"arxiv_id":"2506.02362","last_updated":"2025-06-03T01:37:09Z","snapshot_observed_at":"2026-08-13T05:58:16.125055Z","submitted_at":"2025-06-03T01:37:09Z","title":"MISLEADER: Defending against Model Extraction with Ensembles of Distilled Models","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-07T11:29:43.933632Z"},"links":{"citing_paper":"/paper/2506.02362"},"observation_digest":"sha256:7bdd44537a58433945cb657686f9a6cf885987b54ab1ccc012ae67c10be79b52","observation_id":"360b649d-826d-47d2-93d2-9288587b41ed","resolution":{"observed_at":"2026-08-07T11:29:55.202338Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1503.02531","last_updated":"2015-03-09T15:44:49Z","snapshot_observed_at":"2026-08-14T22:57:08.956233Z","submitted_at":"2015-03-09T15:44:49Z","title":"Distilling the Knowledge in a Neural Network","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1503.02531","snapshot_observed_at":"2026-08-07T11:29:44.014750Z","title":"Distilling the knowledge in a neural network","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2506.02362","last_updated":"2025-06-03T01:37:09Z","snapshot_observed_at":"2026-08-13T05:58:16.125055Z","submitted_at":"2025-06-03T01:37:09Z","title":"MISLEADER: Defending against Model Extraction with Ensembles of Distilled Models","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-07T11:29:44.014750Z"},"links":{"cited_paper":"/paper/1503.02531","citing_paper":"/paper/2506.02362"},"observation_digest":"sha256:7e4d809761692795bc3bca7e30ed618c77e40336dc5c46522266190eccf669b6","observation_id":"237dbdeb-8571-40fd-bd3b-d76d7054ec25","resolution":{"observed_at":"2026-08-07T11:29:44.014750Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T11:29:55.177984Z","title":"Learning to learn from apis: Black-box data-free meta-learning","venue":null,"work_id":"cdf11c99-0a09-4ce1-8e11-03f94636de2e","year":2023},"citing_paper":{"arxiv_id":"2506.02362","last_updated":"2025-06-03T01:37:09Z","snapshot_observed_at":"2026-08-13T05:58:16.125055Z","submitted_at":"2025-06-03T01:37:09Z","title":"MISLEADER: Defending against Model Extraction with Ensembles of Distilled Models","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-07T11:29:44.069042Z"},"links":{"citing_paper":"/paper/2506.02362"},"observation_digest":"sha256:7d58038e8b6dba7875abe184d5ca62fff4048ae34d3f1d2d2d661c319603d2c0","observation_id":"30a2ff01-83d9-4c90-a8f9-89c8f82635fd","resolution":{"observed_at":"2026-08-07T11:29:55.184692Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T11:29:44.142842Z","title":"Densely connected convolutional networks","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2506.02362","last_updated":"2025-06-03T01:37:09Z","snapshot_observed_at":"2026-08-13T05:58:16.125055Z","submitted_at":"2025-06-03T01:37:09Z","title":"MISLEADER: Defending against Model Extraction with Ensembles of Distilled Models","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-07T11:29:44.142842Z"},"links":{"citing_paper":"/paper/2506.02362"},"observation_digest":"sha256:90f8694e81b294e2235891f20b0e98be82f260d05f14865ed3a1aef25c3f12f3","observation_id":"a0eb8dd1-8ebe-4440-98b0-1f1accb9c403","resolution":{"observed_at":"2026-08-07T11:29:44.142842Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T11:29:55.149242Z","title":"High accuracy and high fidelity extraction of neural networks","venue":null,"work_id":"1bbbd350-608d-44a8-b591-082b0f2a4615","year":2020},"citing_paper":{"arxiv_id":"2506.02362","last_updated":"2025-06-03T01:37:09Z","snapshot_observed_at":"2026-08-13T05:58:16.125055Z","submitted_at":"2025-06-03T01:37:09Z","title":"MISLEADER: Defending against Model Extraction with Ensembles of Distilled Models","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-07T11:29:44.212973Z"},"links":{"citing_paper":"/paper/2506.02362"},"observation_digest":"sha256:358bea0281c1e2b7d24c1ec246bc6063756a534792887c5837edd4ae85f8b5b1","observation_id":"1ee8aefd-9dfe-4e30-ada2-4bdd7f01e201","resolution":{"observed_at":"2026-08-07T11:29:55.154429Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T11:29:55.133036Z","title":"A comprehensive defense framework against model extraction attacks.IEEE Transactions on Dependable and Secure Computing, 21(2):685–700, 2023","venue":null,"work_id":"3a81bcf8-10bb-436f-ae06-6edab92766e0","year":2023},"citing_paper":{"arxiv_id":"2506.02362","last_updated":"2025-06-03T01:37:09Z","snapshot_observed_at":"2026-08-13T05:58:16.125055Z","submitted_at":"2025-06-03T01:37:09Z","title":"MISLEADER: Defending against Model Extraction with Ensembles of Distilled Models","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-07T11:29:44.290721Z"},"links":{"citing_paper":"/paper/2506.02362"},"observation_digest":"sha256:adb984f02b093e94cbc756badb6fdb83c5735e849334b5c54b709944572225fe","observation_id":"808ccce3-1d0b-4dc7-b312-c9530357ddec","resolution":{"observed_at":"2026-08-07T11:29:55.138246Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T11:29:55.058122Z","title":"Prada: protecting against dnn model stealing attacks","venue":null,"work_id":"7352ca34-3643-4f1e-9eb2-651ca4f15496","year":2019},"citing_paper":{"arxiv_id":"2506.02362","last_updated":"2025-06-03T01:37:09Z","snapshot_observed_at":"2026-08-13T05:58:16.125055Z","submitted_at":"2025-06-03T01:37:09Z","title":"MISLEADER: Defending against Model Extraction with Ensembles of Distilled Models","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-07T11:29:44.362445Z"},"links":{"citing_paper":"/paper/2506.02362"},"observation_digest":"sha256:55d620646b457c785803290fbbfd026e0f4259ee1fdcf6a65d419a216976d6b3","observation_id":"81706863-f513-4aba-a4f3-f4af169e4e8b","resolution":{"observed_at":"2026-08-07T11:29:55.104879Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T11:29:54.883115Z","title":"Maze: Data-free model stealing attack using zeroth-order gradient estimation","venue":null,"work_id":"4a761550-5f22-4dce-a4ee-5117c23c7997","year":2021},"citing_paper":{"arxiv_id":"2506.02362","last_updated":"2025-06-03T01:37:09Z","snapshot_observed_at":"2026-08-13T05:58:16.125055Z","submitted_at":"2025-06-03T01:37:09Z","title":"MISLEADER: Defending against Model Extraction with Ensembles of Distilled Models","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-07T11:29:44.428306Z"},"links":{"citing_paper":"/paper/2506.02362"},"observation_digest":"sha256:6883664544c833aa681f88706bd66ae9e7e008b51ac1250deb8b7ba40dfdb0ba","observation_id":"1beb6478-54f6-405c-9fa9-a0152c35184b","resolution":{"observed_at":"2026-08-07T11:29:54.977984Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T11:29:54.727447Z","title":"Protecting dnns from theft using an ensemble of diverse models","venue":null,"work_id":"e89f95d3-5fb7-47a2-a648-d04de63c5c77","year":2021},"citing_paper":{"arxiv_id":"2506.02362","last_updated":"2025-06-03T01:37:09Z","snapshot_observed_at":"2026-08-13T05:58:16.125055Z","submitted_at":"2025-06-03T01:37:09Z","title":"MISLEADER: Defending against Model Extraction with Ensembles of Distilled Models","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-07T11:29:44.522479Z"},"links":{"citing_paper":"/paper/2506.02362"},"observation_digest":"sha256:49197cc5bccaf85528b5d349782edf0d39261c531f3b5aee13bf6e6e9bd8dce1","observation_id":"5f09adf9-dcb7-4d48-9041-4598d94e609c","resolution":{"observed_at":"2026-08-07T11:29:54.798480Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T11:29:44.591416Z","title":"Defending against model stealing attacks with adaptive misinformation","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2506.02362","last_updated":"2025-06-03T01:37:09Z","snapshot_observed_at":"2026-08-13T05:58:16.125055Z","submitted_at":"2025-06-03T01:37:09Z","title":"MISLEADER: Defending against Model Extraction with Ensembles of Distilled Models","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-07T11:29:44.591416Z"},"links":{"citing_paper":"/paper/2506.02362"},"observation_digest":"sha256:d6ca5be431f3e05e3b431aeb0f4889b9e551c7bee3f70915551ded8e5d22c30a","observation_id":"3955441e-2fd8-43a1-90d3-71bf3e8bf34e","resolution":{"observed_at":"2026-08-07T11:29:44.591416Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T11:29:54.606311Z","title":"Model extraction warning in mlaas paradigm","venue":null,"work_id":"2e506e4c-2932-4b9d-ba6f-ecc4e38c4519","year":2018},"citing_paper":{"arxiv_id":"2506.02362","last_updated":"2025-06-03T01:37:09Z","snapshot_observed_at":"2026-08-13T05:58:16.125055Z","submitted_at":"2025-06-03T01:37:09Z","title":"MISLEADER: Defending against Model Extraction with Ensembles of Distilled Models","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-07T11:29:44.638468Z"},"links":{"citing_paper":"/paper/2506.02362"},"observation_digest":"sha256:fc3802cd360edba5a75713eda5aed66a9a94c7563b82fca1661d636b8905322f","observation_id":"88cf8439-7dd9-4013-997b-8cee12db35d0","resolution":{"observed_at":"2026-08-07T11:29:54.641699Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1810.09957","last_updated":"2018-10-08T04:30:44Z","snapshot_observed_at":"2026-08-14T18:18:13.301744Z","submitted_at":"2018-10-08T04:30:44Z","title":"NSML: Meet the MLaaS platform with a real-world case study","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1810.09957","snapshot_observed_at":"2026-08-07T11:29:44.746123Z","title":"Nsml: Meet the mlaas platform with a real-world case study.arXiv preprint arXiv:1810.09957, 2018","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.02362","last_updated":"2025-06-03T01:37:09Z","snapshot_observed_at":"2026-08-13T05:58:16.125055Z","submitted_at":"2025-06-03T01:37:09Z","title":"MISLEADER: Defending against Model Extraction with Ensembles of Distilled Models","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-07T11:29:44.746123Z"},"links":{"cited_paper":"/paper/1810.09957","citing_paper":"/paper/2506.02362"},"observation_digest":"sha256:331e269441fc1f200a79390b14d8c3032ad6e4b4314b2424d7e7c1cbbe4c2969","observation_id":"6618bcec-d434-4885-996c-5257588e200a","resolution":{"observed_at":"2026-08-07T11:29:44.746123Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T11:29:44.852634Z","title":"Learning multiple layers of features from tiny images","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2506.02362","last_updated":"2025-06-03T01:37:09Z","snapshot_observed_at":"2026-08-13T05:58:16.125055Z","submitted_at":"2025-06-03T01:37:09Z","title":"MISLEADER: Defending against Model Extraction with Ensembles of Distilled Models","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-07T11:29:44.852634Z"},"links":{"citing_paper":"/paper/2506.02362"},"observation_digest":"sha256:fa1072539c80c1fae5859d6441ffddb2f1196bffde711fe5d52f9cdd01cdfc5c","observation_id":"73a7fe6d-21f5-4f2f-a3b8-5414edb419ed","resolution":{"observed_at":"2026-08-07T11:29:44.852634Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T11:29:54.463268Z","title":"An ensemble approach for classification and prediction of diabetes mellitus using soft voting classifier.International Journal of Cognitive Computing in Engineering, 2:40–46, 2021","venue":null,"work_id":"338311b3-5db9-46e4-a9f3-b4d511636a07","year":2021},"citing_paper":{"arxiv_id":"2506.02362","last_updated":"2025-06-03T01:37:09Z","snapshot_observed_at":"2026-08-13T05:58:16.125055Z","submitted_at":"2025-06-03T01:37:09Z","title":"MISLEADER: Defending against Model Extraction with Ensembles of Distilled Models","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-07T11:29:44.946695Z"},"links":{"citing_paper":"/paper/2506.02362"},"observation_digest":"sha256:5410ce72d345c4e56ea89418bb5536b771fab45b9c75d0f00640e6c581d6fed8","observation_id":"fe4c7ba1-a2ba-4621-beaf-3968cc1f29ae","resolution":{"observed_at":"2026-08-07T11:29:54.518261Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T11:29:54.326410Z","title":"Defending against model extraction attacks with physical unclonable function.Information Sciences, 628:196–207, 2023","venue":null,"work_id":"08d4d6f8-016b-4494-9bf0-a482c6bf03a8","year":2023},"citing_paper":{"arxiv_id":"2506.02362","last_updated":"2025-06-03T01:37:09Z","snapshot_observed_at":"2026-08-13T05:58:16.125055Z","submitted_at":"2025-06-03T01:37:09Z","title":"MISLEADER: Defending against Model Extraction with Ensembles of Distilled Models","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-07T11:29:45.005236Z"},"links":{"citing_paper":"/paper/2506.02362"},"observation_digest":"sha256:ea4b598f18c0d36bab40f8d430d85872c5632218b3ed4ca061fdf94739a5c7ce","observation_id":"f5cddcb3-116c-4e84-ba76-b0d8c9c1f670","resolution":{"observed_at":"2026-08-07T11:29:54.362252Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T11:29:54.194203Z","title":"PhD thesis, Nanyang Technological University, 2025","venue":null,"work_id":"3d6cec5e-b285-409a-9df3-085b2d2f0909","year":2025},"citing_paper":{"arxiv_id":"2506.02362","last_updated":"2025-06-03T01:37:09Z","snapshot_observed_at":"2026-08-13T05:58:16.125055Z","submitted_at":"2025-06-03T01:37:09Z","title":"MISLEADER: Defending against Model Extraction with Ensembles of Distilled Models","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-07T11:29:45.136130Z"},"links":{"citing_paper":"/paper/2506.02362"},"observation_digest":"sha256:a2063b87081a2c55923639425b430610800751f3bae45fa56c95678933eb41f7","observation_id":"d443e543-093d-48c1-ad5e-cad525dc2094","resolution":{"observed_at":"2026-08-07T11:29:54.240412Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T11:29:54.094757Z","title":"Defending against model extraction attacks with ood feature learning and decision boundary confusion.Computers & Security, 136:103563, 2024","venue":null,"work_id":"240b08eb-5e80-4bbb-81ee-2ccf8847c3f2","year":2024},"citing_paper":{"arxiv_id":"2506.02362","last_updated":"2025-06-03T01:37:09Z","snapshot_observed_at":"2026-08-13T05:58:16.125055Z","submitted_at":"2025-06-03T01:37:09Z","title":"MISLEADER: Defending against Model Extraction with Ensembles of Distilled Models","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-07T11:29:45.251316Z"},"links":{"citing_paper":"/paper/2506.02362"},"observation_digest":"sha256:3db4d9b3ff6bcdb8d3572790b0aefb73ccc526b78f4eb5c1988a253aed1b863f","observation_id":"bd4ea582-1b84-450d-a09c-38891304ff16","resolution":{"observed_at":"2026-08-07T11:29:54.115666Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T11:29:45.383709Z","title":"Model extraction attacks revisited","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.02362","last_updated":"2025-06-03T01:37:09Z","snapshot_observed_at":"2026-08-13T05:58:16.125055Z","submitted_at":"2025-06-03T01:37:09Z","title":"MISLEADER: Defending against Model Extraction with Ensembles of Distilled Models","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-07T11:29:45.383709Z"},"links":{"citing_paper":"/paper/2506.02362"},"observation_digest":"sha256:0169d2e3800a11241c5ad6a144b568ac4f32f7883aedb02c5685be519441b26e","observation_id":"43951b68-0877-4be8-875a-76f137355351","resolution":{"observed_at":"2026-08-07T11:29:45.383709Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T11:29:53.920404Z","title":"Quda: Query-limited data-free model extraction","venue":null,"work_id":"ee5f4cc5-bd99-4c93-ade2-20df0516d9e6","year":2023},"citing_paper":{"arxiv_id":"2506.02362","last_updated":"2025-06-03T01:37:09Z","snapshot_observed_at":"2026-08-13T05:58:16.125055Z","submitted_at":"2025-06-03T01:37:09Z","title":"MISLEADER: Defending against Model Extraction with Ensembles of Distilled Models","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-07T11:29:45.461472Z"},"links":{"citing_paper":"/paper/2506.02362"},"observation_digest":"sha256:6d251938aa2bf9148c0bc019cd5384d736904c402d557733d394d9082cacc5be","observation_id":"8baa84a2-ce0d-4bb3-b2e8-0f4f0f62093d","resolution":{"observed_at":"2026-08-07T11:29:54.057746Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T11:29:53.625432Z","title":"Model extraction attack and defense on deep generative models","venue":null,"work_id":"ced7f8dd-6efd-4232-87a5-bcdd96912e95","year":2022},"citing_paper":{"arxiv_id":"2506.02362","last_updated":"2025-06-03T01:37:09Z","snapshot_observed_at":"2026-08-13T05:58:16.125055Z","submitted_at":"2025-06-03T01:37:09Z","title":"MISLEADER: Defending against Model Extraction with Ensembles of Distilled Models","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-07T11:29:45.555517Z"},"links":{"citing_paper":"/paper/2506.02362"},"observation_digest":"sha256:69f66ba075e22856453d40c767acad15ac4f437798a76c6059da43cd90bf54bb","observation_id":"4f23fa17-4653-46b4-b192-46ce5dd9a5b8","resolution":{"observed_at":"2026-08-07T11:29:53.771059Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1608.03983","last_updated":"2017-05-03T16:28:09Z","snapshot_observed_at":"2026-07-06T05:06:55.589962Z","submitted_at":"2016-08-13T13:46:05Z","title":"SGDR: Stochastic Gradient Descent with Warm Restarts","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1608.03983","snapshot_observed_at":"2026-08-07T11:29:45.638448Z","title":"Sgdr: Stochastic gradient descent with warm restarts.arXiv preprint arXiv:1608.03983, 2016","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2506.02362","last_updated":"2025-06-03T01:37:09Z","snapshot_observed_at":"2026-08-13T05:58:16.125055Z","submitted_at":"2025-06-03T01:37:09Z","title":"MISLEADER: Defending against Model Extraction with Ensembles of Distilled Models","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-07T11:29:45.638448Z"},"links":{"cited_paper":"/paper/1608.03983","citing_paper":"/paper/2506.02362"},"observation_digest":"sha256:bb4bc354b1169067d00bc6ea09d83ef3b6753bf5451b04407f7567bdcb261010","observation_id":"cb1dd927-8bca-4b6d-b6dc-237b57b43496","resolution":{"observed_at":"2026-08-07T11:29:45.638448Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T11:29:53.287321Z","title":"Dynamic neural fortresses: An adaptive shield for model extraction defense","venue":null,"work_id":"3ba7d3ef-7081-4b2c-9512-54bb8f0b9c7a","year":null},"citing_paper":{"arxiv_id":"2506.02362","last_updated":"2025-06-03T01:37:09Z","snapshot_observed_at":"2026-08-13T05:58:16.125055Z","submitted_at":"2025-06-03T01:37:09Z","title":"MISLEADER: Defending against Model Extraction with Ensembles of Distilled Models","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-07T11:29:45.719862Z"},"links":{"citing_paper":"/paper/2506.02362"},"observation_digest":"sha256:dec4b509b3eeb5b11b0e02013aba8ad1b26f490cd67f10e70d17246603e1ef49","observation_id":"f562e1f9-6a63-46ce-9c48-6ee40a31722e","resolution":{"observed_at":"2026-08-07T11:29:53.456411Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2104.10706","last_updated":"2021-04-21T18:12:18Z","snapshot_observed_at":"2026-08-11T21:23:50.114825Z","submitted_at":"2021-04-21T18:12:18Z","title":"Dataset Inference: Ownership Resolution in Machine Learning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2104.10706","snapshot_observed_at":"2026-08-07T11:29:45.809923Z","title":"Dataset inference: Ownership resolution in machine learning.arXiv preprint arXiv:2104.10706, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2506.02362","last_updated":"2025-06-03T01:37:09Z","snapshot_observed_at":"2026-08-13T05:58:16.125055Z","submitted_at":"2025-06-03T01:37:09Z","title":"MISLEADER: Defending against Model Extraction with Ensembles of Distilled Models","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-07T11:29:45.809923Z"},"links":{"cited_paper":"/paper/2104.10706","citing_paper":"/paper/2506.02362"},"observation_digest":"sha256:07927bb1327955a1e884bb21e45f137b9f07dcbf23a6d9c33514a192b99aabbd","observation_id":"f0bec78b-5abf-4f04-b142-b25cbf44dff8","resolution":{"observed_at":"2026-08-07T11:29:45.809923Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T11:29:45.889360Z","title":"How to steer your adversary: Targeted and efficient model stealing defenses with gradient redirection","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.02362","last_updated":"2025-06-03T01:37:09Z","snapshot_observed_at":"2026-08-13T05:58:16.125055Z","submitted_at":"2025-06-03T01:37:09Z","title":"MISLEADER: Defending against Model Extraction with Ensembles of Distilled Models","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-07T11:29:45.889360Z"},"links":{"citing_paper":"/paper/2506.02362"},"observation_digest":"sha256:61c652d40dd3177ef3bedeb89aa55d8d12f5a6c043843c5311fc4983aef7b08d","observation_id":"9674f173-d260-4e28-aa78-1212ee20ce3b","resolution":{"observed_at":"2026-08-07T11:29:45.889360Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1710.03740","last_updated":"2018-02-15T20:04:02Z","snapshot_observed_at":"2026-08-12T13:00:33.339808Z","submitted_at":"2017-10-10T17:42:04Z","title":"Mixed Precision Training","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1710.03740","snapshot_observed_at":"2026-08-07T11:29:45.960731Z","title":"Mixed precision training.arXiv preprint arXiv:1710.03740, 2017","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.02362","last_updated":"2025-06-03T01:37:09Z","snapshot_observed_at":"2026-08-13T05:58:16.125055Z","submitted_at":"2025-06-03T01:37:09Z","title":"MISLEADER: Defending against Model Extraction with Ensembles of Distilled Models","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-07T11:29:45.960731Z"},"links":{"cited_paper":"/paper/1710.03740","citing_paper":"/paper/2506.02362"},"observation_digest":"sha256:9c0b167dcba12b51c36db339ab6ec705d516b950b30cf67c97f1a5a12d6ea311","observation_id":"38841a3d-9dc2-47e3-98bf-60f0746a90df","resolution":{"observed_at":"2026-08-07T11:29:45.960731Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T11:29:52.924440Z","title":"Megex: Data-free model extraction attack against gradient-based explainable ai","venue":null,"work_id":"fd28edeb-1a1a-42c0-85f9-44ef93c937ef","year":2024},"citing_paper":{"arxiv_id":"2506.02362","last_updated":"2025-06-03T01:37:09Z","snapshot_observed_at":"2026-08-13T05:58:16.125055Z","submitted_at":"2025-06-03T01:37:09Z","title":"MISLEADER: Defending against Model Extraction with Ensembles of Distilled Models","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-07T11:29:46.061903Z"},"links":{"citing_paper":"/paper/2506.02362"},"observation_digest":"sha256:f0ae814e439007b8225ea9fa84a769bd33d7cd5790cdd4195f92f4007fdfcb84","observation_id":"07a5608d-af51-4df9-a12d-4e48c60259e5","resolution":{"observed_at":"2026-08-07T11:29:53.111340Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T11:29:52.707035Z","title":"The MIT Press, 2nd edition, 2018","venue":null,"work_id":"2f5189d2-ee02-47d7-9ff3-d31398d0b462","year":2018},"citing_paper":{"arxiv_id":"2506.02362","last_updated":"2025-06-03T01:37:09Z","snapshot_observed_at":"2026-08-13T05:58:16.125055Z","submitted_at":"2025-06-03T01:37:09Z","title":"MISLEADER: Defending against Model Extraction with Ensembles of Distilled Models","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-07T11:29:46.157255Z"},"links":{"citing_paper":"/paper/2506.02362"},"observation_digest":"sha256:41cf5ec67a5967d24e86ba6712226513fe5399230287a97afa7725251f5ae1b1","observation_id":"dc245ebc-7ae6-4888-8f4f-737b6e094c16","resolution":{"observed_at":"2026-08-07T11:29:52.781143Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T11:29:52.660015Z","title":"PhD thesis, Technische Universität Wien, 2023","venue":null,"work_id":"90fcbd92-a0f9-49f0-a947-12dbed972ec8","year":2023},"citing_paper":{"arxiv_id":"2506.02362","last_updated":"2025-06-03T01:37:09Z","snapshot_observed_at":"2026-08-13T05:58:16.125055Z","submitted_at":"2025-06-03T01:37:09Z","title":"MISLEADER: Defending against Model Extraction with Ensembles of Distilled Models","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-07T11:29:46.294026Z"},"links":{"citing_paper":"/paper/2506.02362"},"observation_digest":"sha256:1799765c6d475244b801fb1180e5f37938e2d2b3451c1304e0611874779b25b9","observation_id":"a7bd935f-e061-422c-baf9-b48e639436c0","resolution":{"observed_at":"2026-08-07T11:29:52.694587Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T11:29:46.405187Z","title":"Knockoff nets: Stealing functionality of black-box models","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2506.02362","last_updated":"2025-06-03T01:37:09Z","snapshot_observed_at":"2026-08-13T05:58:16.125055Z","submitted_at":"2025-06-03T01:37:09Z","title":"MISLEADER: Defending against Model Extraction with Ensembles of Distilled Models","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-07T11:29:46.405187Z"},"links":{"citing_paper":"/paper/2506.02362"},"observation_digest":"sha256:843617285cb3f79d767fc5e4ba044fbd3949124d728d488a5df448993637ad91","observation_id":"022aa366-53cd-474e-bf7d-bcf7dc2eccb7","resolution":{"observed_at":"2026-08-07T11:29:46.405187Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1906.10908","last_updated":"2020-03-03T10:51:12Z","snapshot_observed_at":"2026-08-14T16:11:25.121636Z","submitted_at":"2019-06-26T08:32:37Z","title":"Prediction Poisoning: Towards Defenses Against DNN Model Stealing Attacks","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1906.10908","snapshot_observed_at":"2026-08-07T11:29:46.552480Z","title":"Prediction poisoning: Towards defenses against dnn model stealing attacks.arXiv preprint arXiv:1906.10908, 2019","venue":null,"work_id":null,"year":1906},"citing_paper":{"arxiv_id":"2506.02362","last_updated":"2025-06-03T01:37:09Z","snapshot_observed_at":"2026-08-13T05:58:16.125055Z","submitted_at":"2025-06-03T01:37:09Z","title":"MISLEADER: Defending against Model Extraction with Ensembles of Distilled Models","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-07T11:29:46.552480Z"},"links":{"cited_paper":"/paper/1906.10908","citing_paper":"/paper/2506.02362"},"observation_digest":"sha256:fdbadd10b2b52255cd405598049a79e99b82fad65a2415706aea6fa9fe8ce71c","observation_id":"65aca9c0-a9e8-4ee8-93e7-fbd27e69b3f9","resolution":{"observed_at":"2026-08-07T11:29:46.552480Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T11:29:52.497006Z","title":"Mod- elshield: Adaptive and robust watermark against model extraction attack.IEEE Transactions on Information Forensics and Security, 2025","venue":null,"work_id":"170e7fb5-4979-40e7-a194-b3e482aca529","year":2025},"citing_paper":{"arxiv_id":"2506.02362","last_updated":"2025-06-03T01:37:09Z","snapshot_observed_at":"2026-08-13T05:58:16.125055Z","submitted_at":"2025-06-03T01:37:09Z","title":"MISLEADER: Defending against Model Extraction with Ensembles of Distilled Models","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-07T11:29:46.696929Z"},"links":{"citing_paper":"/paper/2506.02362"},"observation_digest":"sha256:7418ded7789dced2d7fa7edfccfb29363a7cf95d39113fc1234af4cd8fa2a81d","observation_id":"08f13667-6af2-48e7-91f2-ac6a2f8a4025","resolution":{"observed_at":"2026-08-07T11:29:52.574431Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T11:29:46.841381Z","title":"Practical black-box attacks against machine learning","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2506.02362","last_updated":"2025-06-03T01:37:09Z","snapshot_observed_at":"2026-08-13T05:58:16.125055Z","submitted_at":"2025-06-03T01:37:09Z","title":"MISLEADER: Defending against Model Extraction with Ensembles of Distilled Models","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-07T11:29:46.841381Z"},"links":{"citing_paper":"/paper/2506.02362"},"observation_digest":"sha256:60c5b01eca49e0ecf3b62d635ab044da28e9d7a4de4ad1fdd21b625df9792a4e","observation_id":"ce321895-d395-4e4c-b557-f5a060d3255c","resolution":{"observed_at":"2026-08-07T11:29:46.841381Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T11:29:46.989656Z","title":"Relational knowledge distillation","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2506.02362","last_updated":"2025-06-03T01:37:09Z","snapshot_observed_at":"2026-08-13T05:58:16.125055Z","submitted_at":"2025-06-03T01:37:09Z","title":"MISLEADER: Defending against Model Extraction with Ensembles of Distilled Models","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-07T11:29:46.989656Z"},"links":{"citing_paper":"/paper/2506.02362"},"observation_digest":"sha256:ff275cdda2a3eddd22fee720293828634a04959681785e47de049c35dae0b921","observation_id":"7f57c3fd-0138-41fa-abc5-525e67ddcc6a","resolution":{"observed_at":"2026-08-07T11:29:46.989656Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T11:29:47.088565Z","title":"Automatic differentiation in pytorch","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2506.02362","last_updated":"2025-06-03T01:37:09Z","snapshot_observed_at":"2026-08-13T05:58:16.125055Z","submitted_at":"2025-06-03T01:37:09Z","title":"MISLEADER: Defending against Model Extraction with Ensembles of Distilled Models","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-07T11:29:47.088565Z"},"links":{"citing_paper":"/paper/2506.02362"},"observation_digest":"sha256:193631fd808cc8311f7c765c017845adbec9dce8478e9340f4cad7d6bd43d963","observation_id":"2b2e1da6-907e-46ba-896e-e8e6c79b96b5","resolution":{"observed_at":"2026-08-07T11:29:47.088565Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T11:29:52.351128Z","title":"Mlaas: Machine learning as a service","venue":null,"work_id":"ed5e0378-048e-43d6-bffb-1f681e73d949","year":2015},"citing_paper":{"arxiv_id":"2506.02362","last_updated":"2025-06-03T01:37:09Z","snapshot_observed_at":"2026-08-13T05:58:16.125055Z","submitted_at":"2025-06-03T01:37:09Z","title":"MISLEADER: Defending against Model Extraction with Ensembles of Distilled Models","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-07T11:29:47.213201Z"},"links":{"citing_paper":"/paper/2506.02362"},"observation_digest":"sha256:891b66f4612409065ac2c6ca0bc778d5bc37219758558149409ecf8f5bcc98bb","observation_id":"87d3db77-060a-4b57-9b4e-8a27b012886f","resolution":{"observed_at":"2026-08-07T11:29:52.399547Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T11:29:52.254024Z","title":"Privacy as intellectual property.Stan","venue":null,"work_id":"b998b3fd-6059-4d87-87cd-89dddfa9424a","year":1999},"citing_paper":{"arxiv_id":"2506.02362","last_updated":"2025-06-03T01:37:09Z","snapshot_observed_at":"2026-08-13T05:58:16.125055Z","submitted_at":"2025-06-03T01:37:09Z","title":"MISLEADER: Defending against Model Extraction with Ensembles of Distilled Models","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-07T11:29:47.318207Z"},"links":{"citing_paper":"/paper/2506.02362"},"observation_digest":"sha256:bf7b4f940449a10c20de7fd8e69c6d6c5740043370395fbd1bf1c185576d852a","observation_id":"3d91047b-bac6-4082-b95e-6827687c079d","resolution":{"observed_at":"2026-08-07T11:29:52.283298Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T11:29:47.448509Z","title":"Mobilenetv2: Inverted residuals and linear bottlenecks","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2506.02362","last_updated":"2025-06-03T01:37:09Z","snapshot_observed_at":"2026-08-13T05:58:16.125055Z","submitted_at":"2025-06-03T01:37:09Z","title":"MISLEADER: Defending against Model Extraction with Ensembles of Distilled Models","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-07T11:29:47.448509Z"},"links":{"citing_paper":"/paper/2506.02362"},"observation_digest":"sha256:458dcda55067bcd6a0c5f5539673e791ccd8e888ab950ff559db35edc8c8b8d4","observation_id":"779fd938-78b7-4503-9b3a-c3251d6657c5","resolution":{"observed_at":"2026-08-07T11:29:47.448509Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T11:29:52.124318Z","title":"Towards data-free model stealing in a hard label setting","venue":null,"work_id":"423c24ab-8d61-4d3a-bde5-f72d35573a91","year":2022},"citing_paper":{"arxiv_id":"2506.02362","last_updated":"2025-06-03T01:37:09Z","snapshot_observed_at":"2026-08-13T05:58:16.125055Z","submitted_at":"2025-06-03T01:37:09Z","title":"MISLEADER: Defending against Model Extraction with Ensembles of Distilled Models","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-07T11:29:47.570190Z"},"links":{"citing_paper":"/paper/2506.02362"},"observation_digest":"sha256:2f47af68a9607d2a9f6147ad7c0c5adb4cba233f4012c83be9cd0524e41c846e","observation_id":"a09ea711-c052-4ca0-8b65-5901ecb25f93","resolution":{"observed_at":"2026-08-07T11:29:52.180612Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T11:29:51.994359Z","title":"On efficient training of large-scale deep learning models.ACM Computing Surveys, 57(3):1–36, 2024","venue":null,"work_id":"8aa87d88-3679-4a56-af26-74d336d4526a","year":2024},"citing_paper":{"arxiv_id":"2506.02362","last_updated":"2025-06-03T01:37:09Z","snapshot_observed_at":"2026-08-13T05:58:16.125055Z","submitted_at":"2025-06-03T01:37:09Z","title":"MISLEADER: Defending against Model Extraction with Ensembles of Distilled Models","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-07T11:29:47.719993Z"},"links":{"citing_paper":"/paper/2506.02362"},"observation_digest":"sha256:9f4f746c5326a18ab4077bf30019416232ce639978e411f0f8ffd7fedb9d1eff","observation_id":"97d8357e-3a61-4bce-9494-d1e8cfce3c1b","resolution":{"observed_at":"2026-08-07T11:29:52.049503Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T11:29:51.852986Z","title":"Does knowledge distillation really work?Advances in neural information processing systems, 34:6906–6919, 2021","venue":null,"work_id":"24288f59-6ef4-454e-b0a6-760ad1af8f26","year":2021},"citing_paper":{"arxiv_id":"2506.02362","last_updated":"2025-06-03T01:37:09Z","snapshot_observed_at":"2026-08-13T05:58:16.125055Z","submitted_at":"2025-06-03T01:37:09Z","title":"MISLEADER: Defending against Model Extraction with Ensembles of Distilled Models","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-07T11:29:47.833373Z"},"links":{"citing_paper":"/paper/2506.02362"},"observation_digest":"sha256:3c13bafc4d1db21dc0e098708da8091f7c41b0d0abe1e03c8565280825a5a7bb","observation_id":"b18395a2-b178-42ae-8fd0-71d2ddbe7b94","resolution":{"observed_at":"2026-08-07T11:29:51.910024Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T11:29:51.752221Z","title":"Deep neural network watermarking against model extraction attack","venue":null,"work_id":"626c6722-9d6c-4046-80b9-5e9a4d43306a","year":2023},"citing_paper":{"arxiv_id":"2506.02362","last_updated":"2025-06-03T01:37:09Z","snapshot_observed_at":"2026-08-13T05:58:16.125055Z","submitted_at":"2025-06-03T01:37:09Z","title":"MISLEADER: Defending against Model Extraction with Ensembles of Distilled Models","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-07T11:29:47.959813Z"},"links":{"citing_paper":"/paper/2506.02362"},"observation_digest":"sha256:3caea4a627b4f39ad537f243851b530da20fef4c081b3db36c572f8aed742f13","observation_id":"06f032f6-7550-46ff-9bd2-eb488b2f58e1","resolution":{"observed_at":"2026-08-07T11:29:51.789268Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T11:29:48.095902Z","title":"Stealing machine learning models via prediction {APIs}","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2506.02362","last_updated":"2025-06-03T01:37:09Z","snapshot_observed_at":"2026-08-13T05:58:16.125055Z","submitted_at":"2025-06-03T01:37:09Z","title":"MISLEADER: Defending against Model Extraction with Ensembles of Distilled Models","version":1},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-07T11:29:48.095902Z"},"links":{"citing_paper":"/paper/2506.02362"},"observation_digest":"sha256:46a757e56fcb857309abb32672c408a8a142fa2e52347f20358b2170a11b0906","observation_id":"2f0e70fb-0d69-4c23-b134-697abad43b61","resolution":{"observed_at":"2026-08-07T11:29:48.095902Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T11:29:51.610044Z","title":"Data-free model extraction","venue":null,"work_id":"6ae52030-a4dc-4802-8138-1a81471e92c4","year":2021},"citing_paper":{"arxiv_id":"2506.02362","last_updated":"2025-06-03T01:37:09Z","snapshot_observed_at":"2026-08-13T05:58:16.125055Z","submitted_at":"2025-06-03T01:37:09Z","title":"MISLEADER: Defending against Model Extraction with Ensembles of Distilled Models","version":1},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-07T11:29:48.219035Z"},"links":{"citing_paper":"/paper/2506.02362"},"observation_digest":"sha256:25e9fe0f48f349e179ddf085845ec92c22626824733641767679a95792b1cdde","observation_id":"387f2316-fb70-4fc0-8316-a6da1a7e13cd","resolution":{"observed_at":"2026-08-07T11:29:51.686598Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T11:29:51.502503Z","title":"Defending against data-free model extraction by distributionally robust defensive training.Advances in Neural Information Processing Systems, 36:624–637, 2023","venue":null,"work_id":"935ad437-3ba5-46d7-891f-47841adafe9f","year":2023},"citing_paper":{"arxiv_id":"2506.02362","last_updated":"2025-06-03T01:37:09Z","snapshot_observed_at":"2026-08-13T05:58:16.125055Z","submitted_at":"2025-06-03T01:37:09Z","title":"MISLEADER: Defending against Model Extraction with Ensembles of Distilled Models","version":1},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-07T11:29:48.352974Z"},"links":{"citing_paper":"/paper/2506.02362"},"observation_digest":"sha256:03e0f38c8592e5799a9531793cc22702422cda8e5445a6552a23649461f6bba7","observation_id":"a178aa32-a927-43d1-ab26-826f99153f87","resolution":{"observed_at":"2026-08-07T11:29:51.551622Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T11:29:51.366415Z","title":"Defense against model extraction attack by bayesian active watermarking","venue":null,"work_id":"e96cc408-2d30-408d-ac2e-04bd64de62c4","year":2024},"citing_paper":{"arxiv_id":"2506.02362","last_updated":"2025-06-03T01:37:09Z","snapshot_observed_at":"2026-08-13T05:58:16.125055Z","submitted_at":"2025-06-03T01:37:09Z","title":"MISLEADER: Defending against Model Extraction with Ensembles of Distilled Models","version":1},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-07T11:29:48.477286Z"},"links":{"citing_paper":"/paper/2506.02362"},"observation_digest":"sha256:639a3c62ccf272a8511448f06870536ab8cffa204a9dc783c7e1899f6acd4bbd","observation_id":"72d6f83c-071d-4f74-8ba8-dc106a336bab","resolution":{"observed_at":"2026-08-07T11:29:51.438230Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T11:29:51.140319Z","title":"Zero-shot knowledge distillation from a decision-based black-box model","venue":null,"work_id":"d1189945-914c-406f-8208-706c91358deb","year":2021},"citing_paper":{"arxiv_id":"2506.02362","last_updated":"2025-06-03T01:37:09Z","snapshot_observed_at":"2026-08-13T05:58:16.125055Z","submitted_at":"2025-06-03T01:37:09Z","title":"MISLEADER: Defending against Model Extraction with Ensembles of Distilled Models","version":1},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-08-07T11:29:48.592992Z"},"links":{"citing_paper":"/paper/2506.02362"},"observation_digest":"sha256:9c23a93f9faf89d71eee17a0bcc0fe8d0cd78f51d45d4f8c3478cdafad488c73","observation_id":"d288470e-414c-40f5-b4d6-14a0f1fe3c22","resolution":{"observed_at":"2026-08-07T11:29:51.249330Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T11:29:50.854291Z","title":"Towards explainable model extraction attacks.International Journal of Intelligent Systems, 37(11):9936–9956, 2022","venue":null,"work_id":"7fd18a84-7fd8-433d-9ad8-a1c77c62089b","year":2022},"citing_paper":{"arxiv_id":"2506.02362","last_updated":"2025-06-03T01:37:09Z","snapshot_observed_at":"2026-08-13T05:58:16.125055Z","submitted_at":"2025-06-03T01:37:09Z","title":"MISLEADER: Defending against Model Extraction with Ensembles of Distilled Models","version":1},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-08-07T11:29:48.703182Z"},"links":{"citing_paper":"/paper/2506.02362"},"observation_digest":"sha256:8b89490714b0177b636fe274aef79499108a7556e07cf73db295a984dab72e57","observation_id":"db6c8b70-d670-4426-876a-7ddccb2326e4","resolution":{"observed_at":"2026-08-07T11:29:50.989219Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T11:29:50.617457Z","title":null,"venue":null,"work_id":"5ddf1d7f-c50d-41fe-b5f3-86f40302da1e","year":2023},"citing_paper":{"arxiv_id":"2506.02362","last_updated":"2025-06-03T01:37:09Z","snapshot_observed_at":"2026-08-13T05:58:16.125055Z","submitted_at":"2025-06-03T01:37:09Z","title":"MISLEADER: Defending against Model Extraction with Ensembles of Distilled Models","version":1},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-08-07T11:29:48.807008Z"},"links":{"citing_paper":"/paper/2506.02362"},"observation_digest":"sha256:0e5e47ef56ff4f0ea3fda7a343599db895a1250124cb380aff0a95a7bdb02049","observation_id":"89442633-a36a-4eca-9d97-d71fc9a0d943","resolution":{"observed_at":"2026-08-07T11:29:50.736835Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T11:29:50.341697Z","title":"Mlmodelci: An automatic cloud platform for efficient mlaas","venue":null,"work_id":"d2fa3c34-b5a2-4961-9ba9-f4cac01ab63b","year":2020},"citing_paper":{"arxiv_id":"2506.02362","last_updated":"2025-06-03T01:37:09Z","snapshot_observed_at":"2026-08-13T05:58:16.125055Z","submitted_at":"2025-06-03T01:37:09Z","title":"MISLEADER: Defending against Model Extraction with Ensembles of Distilled Models","version":1},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-08-07T11:29:48.932249Z"},"links":{"citing_paper":"/paper/2506.02362"},"observation_digest":"sha256:d7f69bd3320f2dbbfc21c9b2e88c3b303fe251ef403337184d09963c7ed84b13","observation_id":"19462489-82c2-446b-b2c6-93d1cfabf697","resolution":{"observed_at":"2026-08-07T11:29:50.456875Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T11:29:50.105358Z","title":"Minimizing maximum model discrepancy for transferable black-box targeted attacks","venue":null,"work_id":"8b86085c-7e2d-4ed8-a11e-10147a37c07e","year":2023},"citing_paper":{"arxiv_id":"2506.02362","last_updated":"2025-06-03T01:37:09Z","snapshot_observed_at":"2026-08-13T05:58:16.125055Z","submitted_at":"2025-06-03T01:37:09Z","title":"MISLEADER: Defending against Model Extraction with Ensembles of Distilled Models","version":1},"reference_index":64,"source":"pdf_text","source_observed_at":"2026-08-07T11:29:49.030538Z"},"links":{"citing_paper":"/paper/2506.02362"},"observation_digest":"sha256:eee5bb16e55d49ce8a9606c0ad63ce48636827c656764d7cce67a78285d6813f","observation_id":"261f865e-79f2-4b58-b2d9-217bf6e21583","resolution":{"observed_at":"2026-08-07T11:29:50.234183Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T11:29:49.762119Z","title":"A survey of model extraction attacks and defenses in distributed computing environments, 2025","venue":null,"work_id":"3477b826-058f-4aec-b768-363bbeabe00b","year":2025},"citing_paper":{"arxiv_id":"2506.02362","last_updated":"2025-06-03T01:37:09Z","snapshot_observed_at":"2026-08-13T05:58:16.125055Z","submitted_at":"2025-06-03T01:37:09Z","title":"MISLEADER: Defending against Model Extraction with Ensembles of Distilled Models","version":1},"reference_index":65,"source":"pdf_text","source_observed_at":"2026-08-07T11:29:49.140988Z"},"links":{"citing_paper":"/paper/2506.02362"},"observation_digest":"sha256:b02a80eee3b5a26f5067b8394e023f6d7b242a3e568d4e8c5d273efe18155a33","observation_id":"80f696c6-adf2-4d0a-be40-44fff395ddd4","resolution":{"observed_at":"2026-08-07T11:29:49.864470Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2506.02362","last_updated":"2025-06-03T01:37:09Z","latest_version":1,"primary_category":"cs.CR","snapshot_observed_at":"2026-08-13T05:58:16.125055Z","submitted_at":"2025-06-03T01:37:09Z","title":"MISLEADER: Defending against Model Extraction with Ensembles of Distilled Models"},"reference_resolution":{"displayed":65,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":22,"verified_exact":1,"verified_fuzzy":42},"total_outbound_references":65},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"thesis":"As of 15 August 2026, this Paper Citation Record lists 65 of 65 outbound references and 6 inbound Pith citation observations for arXiv:2506.02362."}