{"as_of":"2026-08-20T19:24:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:d000b4ea4ba9cef3821267bbe8b150de8fff1724d0565262ae4ab899c1eee95e","coverage":[{"denominator":43,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":43,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-12T18:54:57.819552Z","state":"measured"},{"denominator":43,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":43,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-20T06:33:59.587034+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2411.11144/citation-record","integrity":"/paper/2411.11144/integrity","json":"/paper/2411.11144/citation-record.json","paper":"/paper/2411.11144"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T18:54:57.627758Z","title":"Deep learning with differential privacy,","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2411.11144","last_updated":"2024-11-17T18:25:01Z","snapshot_observed_at":"2026-08-19T17:09:54.952097Z","submitted_at":"2024-11-17T18:25:01Z","title":"CLMIA: Membership Inference Attacks via Unsupervised Contrastive Learning","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-12T18:54:57.627758Z"},"links":{"citing_paper":"/paper/2411.11144"},"observation_digest":"sha256:c3f145e41b895c15f6bd41a956b302b9ed56f87c564f184605e63ee82533cb7a","observation_id":"89877994-a8ac-48fb-8275-7192cf126b18","resolution":{"observed_at":"2026-08-12T18:54:57.627758Z","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":"2026-08-12T18:54:57.632852Z","title":"Membership inference attacks from first principles,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2411.11144","last_updated":"2024-11-17T18:25:01Z","snapshot_observed_at":"2026-08-19T17:09:54.952097Z","submitted_at":"2024-11-17T18:25:01Z","title":"CLMIA: Membership Inference Attacks via Unsupervised Contrastive Learning","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-12T18:54:57.632852Z"},"links":{"citing_paper":"/paper/2411.11144"},"observation_digest":"sha256:0151780af81f5783aab90dabd005b7e2834f8fcf53d08ebb078e7a4feb954b30","observation_id":"ae066db7-cff7-46f5-9fc0-0afceb686d12","resolution":{"observed_at":"2026-08-12T18:54:57.632852Z","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":"2026-08-12T18:54:58.525136Z","title":"The secret sharer: Evaluating and testing unintended memorization in neural net- works,","venue":null,"work_id":"bf0fa278-bd58-432d-89c0-121b20589ef2","year":2019},"citing_paper":{"arxiv_id":"2411.11144","last_updated":"2024-11-17T18:25:01Z","snapshot_observed_at":"2026-08-19T17:09:54.952097Z","submitted_at":"2024-11-17T18:25:01Z","title":"CLMIA: Membership Inference Attacks via Unsupervised Contrastive Learning","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-12T18:54:57.637527Z"},"links":{"citing_paper":"/paper/2411.11144"},"observation_digest":"sha256:e6582b992da4e96103abd7e6654d6d655718ef694754c9dcdf2501d5c6e37667","observation_id":"93d1d80a-4a1c-411e-b835-4b46629264ac","resolution":{"observed_at":"2026-08-12T18:54:58.530074Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2207.05801","last_updated":"2022-07-12T19:34:47Z","snapshot_observed_at":"2026-08-19T03:12:00.912470Z","submitted_at":"2022-07-12T19:34:47Z","title":"RelaxLoss: Defending Membership Inference Attacks without Losing Utility","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2207.05801","snapshot_observed_at":"2026-08-12T18:54:57.642124Z","title":"Relaxloss: defending membership infer- ence attacks without losing utility,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2411.11144","last_updated":"2024-11-17T18:25:01Z","snapshot_observed_at":"2026-08-19T17:09:54.952097Z","submitted_at":"2024-11-17T18:25:01Z","title":"CLMIA: Membership Inference Attacks via Unsupervised Contrastive Learning","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-12T18:54:57.642124Z"},"links":{"cited_paper":"/paper/2207.05801","citing_paper":"/paper/2411.11144"},"observation_digest":"sha256:48114e03a8298cbf0c10bb5eaa6b6e46ea2601bec0fcd7019dac463c63b5a573","observation_id":"a06cb806-6156-4522-a979-cbdb0961e20f","resolution":{"observed_at":"2026-08-12T18:54:57.642124Z","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":"2026-08-12T18:54:58.509335Z","title":"Practical membership inference attack against collaborative inference in industrial iot,","venue":null,"work_id":"7a55b665-a53e-4245-a58c-2796d28fc64a","year":2020},"citing_paper":{"arxiv_id":"2411.11144","last_updated":"2024-11-17T18:25:01Z","snapshot_observed_at":"2026-08-19T17:09:54.952097Z","submitted_at":"2024-11-17T18:25:01Z","title":"CLMIA: Membership Inference Attacks via Unsupervised Contrastive Learning","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-12T18:54:57.647469Z"},"links":{"citing_paper":"/paper/2411.11144"},"observation_digest":"sha256:bd0c0507e424c4556e02f735963256465b488746d7b5e4879fbb26393e44dc32","observation_id":"6a41c433-297a-46bc-be70-29062f931204","resolution":{"observed_at":"2026-08-12T18:54:58.514308Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-12T18:54:57.651818Z","title":"A simple framework for contrastive learning of visual representations,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2411.11144","last_updated":"2024-11-17T18:25:01Z","snapshot_observed_at":"2026-08-19T17:09:54.952097Z","submitted_at":"2024-11-17T18:25:01Z","title":"CLMIA: Membership Inference Attacks via Unsupervised Contrastive Learning","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-12T18:54:57.651818Z"},"links":{"citing_paper":"/paper/2411.11144"},"observation_digest":"sha256:a4a477332972d87b82df6391d7158413582962c6042b9023a51bf892f3656c0d","observation_id":"df31b5b6-ed34-4fa5-9876-10aca03a8562","resolution":{"observed_at":"2026-08-12T18:54:57.651818Z","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":"2026-08-12T18:54:58.481913Z","title":"Predicting future earnings changes using machine learning and detailed financial data,","venue":null,"work_id":"476bd92f-b800-4079-8655-659ebaaaaae3","year":2022},"citing_paper":{"arxiv_id":"2411.11144","last_updated":"2024-11-17T18:25:01Z","snapshot_observed_at":"2026-08-19T17:09:54.952097Z","submitted_at":"2024-11-17T18:25:01Z","title":"CLMIA: Membership Inference Attacks via Unsupervised Contrastive Learning","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-12T18:54:57.656873Z"},"links":{"citing_paper":"/paper/2411.11144"},"observation_digest":"sha256:28289499497025dda4f0a956711b11977c32826663db4ae2303aa9934dde85c7","observation_id":"e89c699f-44a4-48ec-825c-37b76d3aa8b5","resolution":{"observed_at":"2026-08-12T18:54:58.486878Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-12T18:54:58.466314Z","title":"Exploring simple siamese representation learning,","venue":null,"work_id":"22ed6303-4292-4702-ac5d-4e2a3712b056","year":2021},"citing_paper":{"arxiv_id":"2411.11144","last_updated":"2024-11-17T18:25:01Z","snapshot_observed_at":"2026-08-19T17:09:54.952097Z","submitted_at":"2024-11-17T18:25:01Z","title":"CLMIA: Membership Inference Attacks via Unsupervised Contrastive Learning","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-12T18:54:57.661418Z"},"links":{"citing_paper":"/paper/2411.11144"},"observation_digest":"sha256:40db669e5462b9a72ec6522d88e2eed145d6951c54c826f9c8bff7aacbd72226","observation_id":"47328948-3030-4117-b0e1-d865c920e35a","resolution":{"observed_at":"2026-08-12T18:54:58.471289Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-12T18:54:58.450798Z","title":"Exploring simple siamese representation learning,","venue":null,"work_id":"a139c437-233d-46a6-bf4e-4393b4bd91b7","year":2021},"citing_paper":{"arxiv_id":"2411.11144","last_updated":"2024-11-17T18:25:01Z","snapshot_observed_at":"2026-08-19T17:09:54.952097Z","submitted_at":"2024-11-17T18:25:01Z","title":"CLMIA: Membership Inference Attacks via Unsupervised Contrastive Learning","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-12T18:54:57.665968Z"},"links":{"citing_paper":"/paper/2411.11144"},"observation_digest":"sha256:37e36d32525da8707639bc71bde894320309aee9547b9e13d44b34662c11b652","observation_id":"a4e2b470-ec8a-4f24-b678-9bb607cc92d4","resolution":{"observed_at":"2026-08-12T18:54:58.455653Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-12T18:54:58.433225Z","title":"Leveraging adversarial examples to quantify membership information leakage,","venue":null,"work_id":"4aae31ec-6c91-4129-a4dd-35de7e2ba69c","year":2022},"citing_paper":{"arxiv_id":"2411.11144","last_updated":"2024-11-17T18:25:01Z","snapshot_observed_at":"2026-08-19T17:09:54.952097Z","submitted_at":"2024-11-17T18:25:01Z","title":"CLMIA: Membership Inference Attacks via Unsupervised Contrastive Learning","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-12T18:54:57.670268Z"},"links":{"citing_paper":"/paper/2411.11144"},"observation_digest":"sha256:6878dd9b2753ee3c93cca559e9d2f7b8da0bcc85ae2b726c9807a7e3a8850168","observation_id":"49f6c73a-1d56-4be2-898f-13a6341c16b0","resolution":{"observed_at":"2026-08-12T18:54:58.438160Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-12T18:54:58.416991Z","title":"Simcse: Simple contrastive learning of sentence embeddings,","venue":null,"work_id":"f67741cb-1116-410f-b3d6-6e4f9796a76a","year":2021},"citing_paper":{"arxiv_id":"2411.11144","last_updated":"2024-11-17T18:25:01Z","snapshot_observed_at":"2026-08-19T17:09:54.952097Z","submitted_at":"2024-11-17T18:25:01Z","title":"CLMIA: Membership Inference Attacks via Unsupervised Contrastive Learning","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-12T18:54:57.674723Z"},"links":{"citing_paper":"/paper/2411.11144"},"observation_digest":"sha256:c94e3498540aa961744ee7ef9e2fc470f5a0ec735bc52dd1272159ee6730fee0","observation_id":"2c2815ef-c130-4db1-ba6e-e74562490892","resolution":{"observed_at":"2026-08-12T18:54:58.422303Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-12T18:54:57.679019Z","title":"Bootstrap your own latent-a new approach to self-supervised learning,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2411.11144","last_updated":"2024-11-17T18:25:01Z","snapshot_observed_at":"2026-08-19T17:09:54.952097Z","submitted_at":"2024-11-17T18:25:01Z","title":"CLMIA: Membership Inference Attacks via Unsupervised Contrastive Learning","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-12T18:54:57.679019Z"},"links":{"citing_paper":"/paper/2411.11144"},"observation_digest":"sha256:420fe0a35d9fff76b50551ff9499c78be68f028d368069f9c13a694390f4435a","observation_id":"eabbac77-304f-41e2-b1f0-c08fd9e2dd6b","resolution":{"observed_at":"2026-08-12T18:54:57.679019Z","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":"2026-08-12T18:54:57.683262Z","title":"Momentum contrast for unsupervised visual representation learning,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2411.11144","last_updated":"2024-11-17T18:25:01Z","snapshot_observed_at":"2026-08-19T17:09:54.952097Z","submitted_at":"2024-11-17T18:25:01Z","title":"CLMIA: Membership Inference Attacks via Unsupervised Contrastive Learning","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-12T18:54:57.683262Z"},"links":{"citing_paper":"/paper/2411.11144"},"observation_digest":"sha256:31917e210f42d0fc102d2b6b3c56b3f2f2bea5ad9dbf459cffa24d0dd699774c","observation_id":"ddcc38e4-b4b7-4d5d-b4bf-4acc945ccd68","resolution":{"observed_at":"2026-08-12T18:54:57.683262Z","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":"2026-08-12T18:54:57.687687Z","title":"Segmentations-leak: Membership inference attacks and defenses in semantic image segmen- tation,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2411.11144","last_updated":"2024-11-17T18:25:01Z","snapshot_observed_at":"2026-08-19T17:09:54.952097Z","submitted_at":"2024-11-17T18:25:01Z","title":"CLMIA: Membership Inference Attacks via Unsupervised Contrastive Learning","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-12T18:54:57.687687Z"},"links":{"citing_paper":"/paper/2411.11144"},"observation_digest":"sha256:b96de16c69445a4b19ad010754b2404b1133c84608203b7d2487c2d2ca280988","observation_id":"1561a008-285d-4bfb-b945-d191e209bd88","resolution":{"observed_at":"2026-08-12T18:54:57.687687Z","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":"2026-08-12T18:54:58.372120Z","title":"Mem- bership inference via backdooring,","venue":null,"work_id":"764c5901-930b-47e9-973c-1e87878bdff6","year":2022},"citing_paper":{"arxiv_id":"2411.11144","last_updated":"2024-11-17T18:25:01Z","snapshot_observed_at":"2026-08-19T17:09:54.952097Z","submitted_at":"2024-11-17T18:25:01Z","title":"CLMIA: Membership Inference Attacks via Unsupervised Contrastive Learning","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-12T18:54:57.691956Z"},"links":{"citing_paper":"/paper/2411.11144"},"observation_digest":"sha256:963d6abeaddcc6234ec4c21152fa02b1a0fd13f5d13adbdeed9f74465a3f6548","observation_id":"15948c6b-1c55-42c8-aafd-b9b5a88a9637","resolution":{"observed_at":"2026-08-12T18:54:58.377191Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-12T18:54:58.356457Z","title":"Practical blind membership inference attack via differential comparisons,","venue":null,"work_id":"3c54e75f-1718-49b4-bc14-cd1570d3ad9f","year":2021},"citing_paper":{"arxiv_id":"2411.11144","last_updated":"2024-11-17T18:25:01Z","snapshot_observed_at":"2026-08-19T17:09:54.952097Z","submitted_at":"2024-11-17T18:25:01Z","title":"CLMIA: Membership Inference Attacks via Unsupervised Contrastive Learning","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-12T18:54:57.696338Z"},"links":{"citing_paper":"/paper/2411.11144"},"observation_digest":"sha256:685922a98f4f50df408221849e45abfa2b2217175e4a12e83010825496e73193","observation_id":"e9e8bd1d-647b-4a07-81f4-5ea76500c662","resolution":{"observed_at":"2026-08-12T18:54:58.361053Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-12T18:54:58.341395Z","title":"Demystifying the membership inference attack,","venue":null,"work_id":"623593f5-c8c4-4d06-8b84-caeecbe63f16","year":2019},"citing_paper":{"arxiv_id":"2411.11144","last_updated":"2024-11-17T18:25:01Z","snapshot_observed_at":"2026-08-19T17:09:54.952097Z","submitted_at":"2024-11-17T18:25:01Z","title":"CLMIA: Membership Inference Attacks via Unsupervised Contrastive Learning","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-12T18:54:57.700696Z"},"links":{"citing_paper":"/paper/2411.11144"},"observation_digest":"sha256:cf9c483e061e5ee05aaa10ab321ce245251a92fc67da8ec69f68d1663d1d60fc","observation_id":"bfc91a05-0617-486e-8813-61b102b52230","resolution":{"observed_at":"2026-08-12T18:54:58.346178Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-12T18:54:58.327127Z","title":"Memguard: Defending against black-box membership inference attacks via adver- sarial examples,","venue":null,"work_id":"c31a56bc-5e83-4904-a089-d44f741d6ba0","year":2019},"citing_paper":{"arxiv_id":"2411.11144","last_updated":"2024-11-17T18:25:01Z","snapshot_observed_at":"2026-08-19T17:09:54.952097Z","submitted_at":"2024-11-17T18:25:01Z","title":"CLMIA: Membership Inference Attacks via Unsupervised Contrastive Learning","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-12T18:54:57.705212Z"},"links":{"citing_paper":"/paper/2411.11144"},"observation_digest":"sha256:8b354b4108b126420cc9d91de88ade57cc16dbf61834904374d7b2175dae0323","observation_id":"2be8d422-7bf8-4e2a-8674-29ed0b5c95f6","resolution":{"observed_at":"2026-08-12T18:54:58.331780Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-12T18:54:58.312032Z","title":"When does data augmentation help with membership inference attacks?","venue":null,"work_id":"caeeb2e7-e35d-445e-8571-b4c09107df79","year":2021},"citing_paper":{"arxiv_id":"2411.11144","last_updated":"2024-11-17T18:25:01Z","snapshot_observed_at":"2026-08-19T17:09:54.952097Z","submitted_at":"2024-11-17T18:25:01Z","title":"CLMIA: Membership Inference Attacks via Unsupervised Contrastive Learning","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-12T18:54:57.709235Z"},"links":{"citing_paper":"/paper/2411.11144"},"observation_digest":"sha256:99ce205d6c3710237654761a111a680673b95c537b1b27a634e8eee779800c41","observation_id":"07e3ef05-b8dc-4de9-a3a4-4155e99b7645","resolution":{"observed_at":"2026-08-12T18:54:58.317026Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2006.05336","last_updated":"2020-06-09T15:17:21Z","snapshot_observed_at":"2026-08-19T01:13:25.770315Z","submitted_at":"2020-06-09T15:17:21Z","title":"On the Effectiveness of Regularization Against Membership Inference Attacks","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2006.05336","snapshot_observed_at":"2026-08-12T18:54:57.714174Z","title":"On the effectiveness of reg- ularization against membership inference attacks,","venue":null,"work_id":null,"year":2006},"citing_paper":{"arxiv_id":"2411.11144","last_updated":"2024-11-17T18:25:01Z","snapshot_observed_at":"2026-08-19T17:09:54.952097Z","submitted_at":"2024-11-17T18:25:01Z","title":"CLMIA: Membership Inference Attacks via Unsupervised Contrastive Learning","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-12T18:54:57.714174Z"},"links":{"cited_paper":"/paper/2006.05336","citing_paper":"/paper/2411.11144"},"observation_digest":"sha256:953e73aa69498fbaff42ff75396db08048eb1f3742ed79ad6d22520c8bc6a113","observation_id":"136e927d-4e51-431e-868d-124e0fb0a82c","resolution":{"observed_at":"2026-08-12T18:54:57.714174Z","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":"2026-08-12T18:54:58.297008Z","title":"Stolen memories: Leveraging model memorization for calibrated {White-Box} membership inference,","venue":null,"work_id":"9022d8e5-3fc9-4ab1-b68a-48580a3b60e3","year":2020},"citing_paper":{"arxiv_id":"2411.11144","last_updated":"2024-11-17T18:25:01Z","snapshot_observed_at":"2026-08-19T17:09:54.952097Z","submitted_at":"2024-11-17T18:25:01Z","title":"CLMIA: Membership Inference Attacks via Unsupervised Contrastive Learning","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-12T18:54:57.719120Z"},"links":{"citing_paper":"/paper/2411.11144"},"observation_digest":"sha256:03b2684fc906f1e9eb1a502c766b2dea9dffa190c371d33a5a3dee0817566f59","observation_id":"0956fc74-6bd3-4c9e-8fe6-37f51a54fcc6","resolution":{"observed_at":"2026-08-12T18:54:58.301695Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2203.02077","last_updated":"2022-04-25T23:59:03Z","snapshot_observed_at":"2026-08-16T17:17:04.308681Z","submitted_at":"2022-03-04T00:49:42Z","title":"User-Level Membership Inference Attack against Metric Embedding Learning","version":2},"cited_work":{"arxiv_id":"2203.02077","doi":null,"metadata_source":"pith","pith_arxiv_id":"2203.02077","snapshot_observed_at":"2026-08-12T18:54:57.984563Z","title":"User-Level Membership Inference Attack against Metric Embedding Learning","venue":"cs.LG","work_id":"f783719a-5382-4d68-ac47-c4f383cadaf3","year":2022},"citing_paper":{"arxiv_id":"2411.11144","last_updated":"2024-11-17T18:25:01Z","snapshot_observed_at":"2026-08-19T17:09:54.952097Z","submitted_at":"2024-11-17T18:25:01Z","title":"CLMIA: Membership Inference Attacks via Unsupervised Contrastive Learning","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-12T18:54:57.723524Z"},"links":{"cited_paper":"/paper/2203.02077","citing_paper":"/paper/2411.11144"},"observation_digest":"sha256:43a2124234c4310b1cc8a20007d997773d4812120c835443b1d92c1b59b9b726","observation_id":"20493039-ead3-4e65-844d-63aebb348456","resolution":{"observed_at":"2026-08-12T18:54:57.991861Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-12T18:54:57.728175Z","title":"Membership inference attacks and defenses in classification models,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2411.11144","last_updated":"2024-11-17T18:25:01Z","snapshot_observed_at":"2026-08-19T17:09:54.952097Z","submitted_at":"2024-11-17T18:25:01Z","title":"CLMIA: Membership Inference Attacks via Unsupervised Contrastive Learning","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-12T18:54:57.728175Z"},"links":{"citing_paper":"/paper/2411.11144"},"observation_digest":"sha256:5ac496bb08bd5757d760552a70345af00ac82e59342cec391b5cc336b8aaca28","observation_id":"8224e8f6-d113-4e30-8f59-7115235c75f4","resolution":{"observed_at":"2026-08-12T18:54:57.728175Z","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":"2026-08-12T18:54:57.732756Z","title":"Membership leakage in label-only exposures,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2411.11144","last_updated":"2024-11-17T18:25:01Z","snapshot_observed_at":"2026-08-19T17:09:54.952097Z","submitted_at":"2024-11-17T18:25:01Z","title":"CLMIA: Membership Inference Attacks via Unsupervised Contrastive Learning","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-12T18:54:57.732756Z"},"links":{"citing_paper":"/paper/2411.11144"},"observation_digest":"sha256:0dfd0099c5a738d131cee6bbcb6686d7dfd2b5ee0396cc1c5aaa37513baaf543","observation_id":"c11bd846-c5b7-4d86-8666-5f750bdead7f","resolution":{"observed_at":"2026-08-12T18:54:57.732756Z","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":"2026-08-12T18:54:58.262701Z","title":"Socinf: Membership inference attacks on social media health data with machine learning,","venue":null,"work_id":"05139e2d-103c-46d5-9c74-6436e076e813","year":2019},"citing_paper":{"arxiv_id":"2411.11144","last_updated":"2024-11-17T18:25:01Z","snapshot_observed_at":"2026-08-19T17:09:54.952097Z","submitted_at":"2024-11-17T18:25:01Z","title":"CLMIA: Membership Inference Attacks via Unsupervised Contrastive Learning","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-12T18:54:57.737404Z"},"links":{"citing_paper":"/paper/2411.11144"},"observation_digest":"sha256:8279446062694a1d36baea69778c911430b4c0a532e44f6dc9ac4282d5c70a66","observation_id":"ec6c2e4e-f1b2-423e-9dc4-3b22fd7caf66","resolution":{"observed_at":"2026-08-12T18:54:58.267296Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-12T18:54:57.742193Z","title":"Membership inference attacks by exploiting loss trajectory,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2411.11144","last_updated":"2024-11-17T18:25:01Z","snapshot_observed_at":"2026-08-19T17:09:54.952097Z","submitted_at":"2024-11-17T18:25:01Z","title":"CLMIA: Membership Inference Attacks via Unsupervised Contrastive Learning","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-12T18:54:57.742193Z"},"links":{"citing_paper":"/paper/2411.11144"},"observation_digest":"sha256:5d78e52fad635bf3c74134c0d3dac5a7cbd61ad274dc9272cf2dacd577aefb58","observation_id":"3157bf97-0ef1-441c-8664-ebfad57eb354","resolution":{"observed_at":"2026-08-12T18:54:57.742193Z","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":"2026-08-12T18:54:57.746843Z","title":"Membership inference attacks by exploiting loss trajectory,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2411.11144","last_updated":"2024-11-17T18:25:01Z","snapshot_observed_at":"2026-08-19T17:09:54.952097Z","submitted_at":"2024-11-17T18:25:01Z","title":"CLMIA: Membership Inference Attacks via Unsupervised Contrastive Learning","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-12T18:54:57.746843Z"},"links":{"citing_paper":"/paper/2411.11144"},"observation_digest":"sha256:80c200ba719b55210b1e813303744690daafb37e739867b8db5fa06f1565693c","observation_id":"0212ee6f-7a6e-4e02-a8a0-0f341a156bd0","resolution":{"observed_at":"2026-08-12T18:54:57.746843Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1802.04889","last_updated":"2018-02-13T23:05:05Z","snapshot_observed_at":"2026-08-14T19:46:08.923996Z","submitted_at":"2018-02-13T23:05:05Z","title":"Understanding Membership Inferences on Well-Generalized Learning Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1802.04889","snapshot_observed_at":"2026-08-12T18:54:57.751270Z","title":"Understanding membership inferences on well- generalized learning models,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2411.11144","last_updated":"2024-11-17T18:25:01Z","snapshot_observed_at":"2026-08-19T17:09:54.952097Z","submitted_at":"2024-11-17T18:25:01Z","title":"CLMIA: Membership Inference Attacks via Unsupervised Contrastive Learning","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-12T18:54:57.751270Z"},"links":{"cited_paper":"/paper/1802.04889","citing_paper":"/paper/2411.11144"},"observation_digest":"sha256:393a48c035a818b6422aa952077bbd4436409654e71fca3e6b5fb7337aaf3cf2","observation_id":"d3abadae-3eac-4111-b9df-18e7ccdffe57","resolution":{"observed_at":"2026-08-12T18:54:57.751270Z","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":"2026-08-12T18:54:58.238026Z","title":"The audio auditor: User-level membership inference in internet of things voice services,","venue":null,"work_id":"e9f4b91d-8cd7-4c22-93da-40f8ba693e0b","year":2021},"citing_paper":{"arxiv_id":"2411.11144","last_updated":"2024-11-17T18:25:01Z","snapshot_observed_at":"2026-08-19T17:09:54.952097Z","submitted_at":"2024-11-17T18:25:01Z","title":"CLMIA: Membership Inference Attacks via Unsupervised Contrastive Learning","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-12T18:54:57.756081Z"},"links":{"citing_paper":"/paper/2411.11144"},"observation_digest":"sha256:0e0dfe65e237035bc28b236b69d531507d48c33ff6219421c9b1e6138481eb28","observation_id":"0776587d-7dd4-4b4e-81ad-70c121db7927","resolution":{"observed_at":"2026-08-12T18:54:58.243162Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-12T18:54:57.760696Z","title":"Comprehensive privacy analysis of deep learning: Passive and active white-box inference attacks against centralized and federated learning,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2411.11144","last_updated":"2024-11-17T18:25:01Z","snapshot_observed_at":"2026-08-19T17:09:54.952097Z","submitted_at":"2024-11-17T18:25:01Z","title":"CLMIA: Membership Inference Attacks via Unsupervised Contrastive Learning","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-12T18:54:57.760696Z"},"links":{"citing_paper":"/paper/2411.11144"},"observation_digest":"sha256:93170887e5f333621ba7af38d112a7c60cc893e2c668c6e1faa8a69f92f21879","observation_id":"9016b324-f22d-4193-b7a4-b93fb98d7f20","resolution":{"observed_at":"2026-08-12T18:54:57.760696Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1708.06145","last_updated":"2017-11-29T11:47:25Z","snapshot_observed_at":"2026-08-14T20:40:18.972494Z","submitted_at":"2017-08-21T10:50:24Z","title":"Knock Knock, Who's There? Membership Inference on Aggregate Location Data","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1708.06145","snapshot_observed_at":"2026-08-12T18:54:57.765307Z","title":"Knock knock, who’s there? membership inference on aggregate location data,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2411.11144","last_updated":"2024-11-17T18:25:01Z","snapshot_observed_at":"2026-08-19T17:09:54.952097Z","submitted_at":"2024-11-17T18:25:01Z","title":"CLMIA: Membership Inference Attacks via Unsupervised Contrastive Learning","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-12T18:54:57.765307Z"},"links":{"cited_paper":"/paper/1708.06145","citing_paper":"/paper/2411.11144"},"observation_digest":"sha256:4d7e3cf050f83c2d23d6193e079664063e8aaeafad5d2490994251cb537d5291","observation_id":"3e7adc52-b810-465e-8b0a-fa849c488c3f","resolution":{"observed_at":"2026-08-12T18:54:57.765307Z","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":"2026-08-12T18:54:58.212778Z","title":"Differential privacy defenses and sampling attacks for membership inference,","venue":null,"work_id":"c999f807-1ccd-4e79-9f96-e789595f2afb","year":2021},"citing_paper":{"arxiv_id":"2411.11144","last_updated":"2024-11-17T18:25:01Z","snapshot_observed_at":"2026-08-19T17:09:54.952097Z","submitted_at":"2024-11-17T18:25:01Z","title":"CLMIA: Membership Inference Attacks via Unsupervised Contrastive Learning","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-12T18:54:57.770025Z"},"links":{"citing_paper":"/paper/2411.11144"},"observation_digest":"sha256:465e8f6216578ca43290d8b579f70770e771231fcc2d3f5a27c401809c0c93f2","observation_id":"6c828998-a2ad-4331-ab8f-068940d7b34e","resolution":{"observed_at":"2026-08-12T18:54:58.217978Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-12T18:54:58.196218Z","title":"White-box vs black-box: Bayes optimal strategies for membership inference,","venue":null,"work_id":"d99daedf-1b8e-4ce8-807b-9707e9672559","year":2019},"citing_paper":{"arxiv_id":"2411.11144","last_updated":"2024-11-17T18:25:01Z","snapshot_observed_at":"2026-08-19T17:09:54.952097Z","submitted_at":"2024-11-17T18:25:01Z","title":"CLMIA: Membership Inference Attacks via Unsupervised Contrastive Learning","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-12T18:54:57.774472Z"},"links":{"citing_paper":"/paper/2411.11144"},"observation_digest":"sha256:3cb71154499842a29714c3a46a4af5cffbb935b9c5c051bb2d79c508c1d86052","observation_id":"c55a4481-9804-4298-a098-8cf5b5c7e7c3","resolution":{"observed_at":"2026-08-12T18:54:58.201474Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-12T18:54:58.180159Z","title":"Ml-leaks: Model and data independent membership inference attacks and defenses on machine learning models,","venue":null,"work_id":"f3fe5fa7-bead-42b8-90e4-4863690d22bc","year":2019},"citing_paper":{"arxiv_id":"2411.11144","last_updated":"2024-11-17T18:25:01Z","snapshot_observed_at":"2026-08-19T17:09:54.952097Z","submitted_at":"2024-11-17T18:25:01Z","title":"CLMIA: Membership Inference Attacks via Unsupervised Contrastive Learning","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-12T18:54:57.778934Z"},"links":{"citing_paper":"/paper/2411.11144"},"observation_digest":"sha256:47887bc405b43a3a80698e8affe38a84c88b18961d85e9e5141cbf8ac4421d05","observation_id":"cbe1b33f-5d89-415a-95ff-72c4d3e4442b","resolution":{"observed_at":"2026-08-12T18:54:58.185248Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-12T18:54:58.164558Z","title":"Evaluating the vulnerability of end-to-end automatic speech recogni- tion models to membership inference attacks","venue":null,"work_id":"f5715844-511a-481e-b102-a930cf81c948","year":2021},"citing_paper":{"arxiv_id":"2411.11144","last_updated":"2024-11-17T18:25:01Z","snapshot_observed_at":"2026-08-19T17:09:54.952097Z","submitted_at":"2024-11-17T18:25:01Z","title":"CLMIA: Membership Inference Attacks via Unsupervised Contrastive Learning","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-12T18:54:57.783285Z"},"links":{"citing_paper":"/paper/2411.11144"},"observation_digest":"sha256:71fd91cdfdf1bdfd92df223ea6cd3741cbba7d9296dffbbda0e80a8e4c673a3a","observation_id":"700440c6-bd46-45cb-8cf1-6aaac1668e05","resolution":{"observed_at":"2026-08-12T18:54:58.169150Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-12T18:54:58.149961Z","title":"Membership inference attacks against machine learning models,","venue":null,"work_id":"b3d98ac7-7771-4c75-b882-37beeed18df8","year":2017},"citing_paper":{"arxiv_id":"2411.11144","last_updated":"2024-11-17T18:25:01Z","snapshot_observed_at":"2026-08-19T17:09:54.952097Z","submitted_at":"2024-11-17T18:25:01Z","title":"CLMIA: Membership Inference Attacks via Unsupervised Contrastive Learning","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-12T18:54:57.787638Z"},"links":{"citing_paper":"/paper/2411.11144"},"observation_digest":"sha256:f97e5381238a8cdd6d0a8241c3a86b49039a0c080c7399d9f0a7871fed5b5349","observation_id":"3c827b07-bb14-4e7e-a061-2e8434c2c7d3","resolution":{"observed_at":"2026-08-12T18:54:58.154913Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-12T18:54:58.135120Z","title":"Systematic evaluation of privacy risks of ma- chine learning models,","venue":null,"work_id":"96e4419b-9260-45b5-8a29-3abb06b06a09","year":2021},"citing_paper":{"arxiv_id":"2411.11144","last_updated":"2024-11-17T18:25:01Z","snapshot_observed_at":"2026-08-19T17:09:54.952097Z","submitted_at":"2024-11-17T18:25:01Z","title":"CLMIA: Membership Inference Attacks via Unsupervised Contrastive Learning","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-12T18:54:57.792411Z"},"links":{"citing_paper":"/paper/2411.11144"},"observation_digest":"sha256:c09cc8f2866b9639b239aa121bc53bb20492b61ba76c68435b71d30c21b296e9","observation_id":"d1d35f68-41b0-4d42-bf1c-3ab2ba8cf637","resolution":{"observed_at":"2026-08-12T18:54:58.140068Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-12T18:54:58.119918Z","title":"Privacy risks of securing machine learning models against adversarial examples,","venue":null,"work_id":"f58d5f65-d5b2-48ef-8808-709a32505760","year":2019},"citing_paper":{"arxiv_id":"2411.11144","last_updated":"2024-11-17T18:25:01Z","snapshot_observed_at":"2026-08-19T17:09:54.952097Z","submitted_at":"2024-11-17T18:25:01Z","title":"CLMIA: Membership Inference Attacks via Unsupervised Contrastive Learning","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-12T18:54:57.796883Z"},"links":{"citing_paper":"/paper/2411.11144"},"observation_digest":"sha256:a1276d231b0181316cae844f076b13eb04040a531b268d8497002ca9780ed5b0","observation_id":"08fb08b1-f422-469c-9303-67293f0b37dd","resolution":{"observed_at":"2026-08-12T18:54:58.124635Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-12T18:54:57.801398Z","title":"Unsupervised feature learning via non-parametric instance discrimination,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2411.11144","last_updated":"2024-11-17T18:25:01Z","snapshot_observed_at":"2026-08-19T17:09:54.952097Z","submitted_at":"2024-11-17T18:25:01Z","title":"CLMIA: Membership Inference Attacks via Unsupervised Contrastive Learning","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-12T18:54:57.801398Z"},"links":{"citing_paper":"/paper/2411.11144"},"observation_digest":"sha256:7b580792c1e39e9355f441b889567611c2f93d46a2f64edf7ac0a62c77f47e59","observation_id":"aa7582c7-b283-4a34-ab0f-c1a040ec3474","resolution":{"observed_at":"2026-08-12T18:54:57.801398Z","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":"2026-08-12T18:54:57.805955Z","title":"Privacy risk in machine learning: Analyzing the connection to overfitting,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2411.11144","last_updated":"2024-11-17T18:25:01Z","snapshot_observed_at":"2026-08-19T17:09:54.952097Z","submitted_at":"2024-11-17T18:25:01Z","title":"CLMIA: Membership Inference Attacks via Unsupervised Contrastive Learning","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-12T18:54:57.805955Z"},"links":{"citing_paper":"/paper/2411.11144"},"observation_digest":"sha256:769853d4fb0e06bdc65b6422c6f209197f1f669bab55f1b21fc2ac9a01c24d7d","observation_id":"164caadb-57c9-4168-a155-775576c978fd","resolution":{"observed_at":"2026-08-12T18:54:57.805955Z","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":"2026-08-12T18:54:58.084735Z","title":"Label-only membership inference attacks and defenses in semantic segmentation models,","venue":null,"work_id":"e48ad130-dd01-4c28-af33-3874f7231a23","year":2022},"citing_paper":{"arxiv_id":"2411.11144","last_updated":"2024-11-17T18:25:01Z","snapshot_observed_at":"2026-08-19T17:09:54.952097Z","submitted_at":"2024-11-17T18:25:01Z","title":"CLMIA: Membership Inference Attacks via Unsupervised Contrastive Learning","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-12T18:54:57.810349Z"},"links":{"citing_paper":"/paper/2411.11144"},"observation_digest":"sha256:0291dff5c26a0bf9fb0f379ab602e524e8e25e8318ddc638ba7c8d4cc557e7c2","observation_id":"b6e9ba71-091a-4f54-9219-a3afec45f582","resolution":{"observed_at":"2026-08-12T18:54:58.089604Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-12T18:54:58.068324Z","title":"Membership inference attacks against recommender systems,","venue":null,"work_id":"1558e951-2dc0-4bc8-83f3-2d146012ef47","year":2021},"citing_paper":{"arxiv_id":"2411.11144","last_updated":"2024-11-17T18:25:01Z","snapshot_observed_at":"2026-08-19T17:09:54.952097Z","submitted_at":"2024-11-17T18:25:01Z","title":"CLMIA: Membership Inference Attacks via Unsupervised Contrastive Learning","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-12T18:54:57.814980Z"},"links":{"citing_paper":"/paper/2411.11144"},"observation_digest":"sha256:2b56f5f99c9ac0b5843fba12aadae1d0edcc498054ce2fc48ed9ed69bbcc3827","observation_id":"f04a5553-1832-4992-b17a-51e5b210f6b4","resolution":{"observed_at":"2026-08-12T18:54:58.073775Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-12T18:54:58.050576Z","title":"Membership inference attacks against synthetic health data,","venue":null,"work_id":"e6533b5c-1ef5-4934-b4a7-bf04e57269ee","year":2022},"citing_paper":{"arxiv_id":"2411.11144","last_updated":"2024-11-17T18:25:01Z","snapshot_observed_at":"2026-08-19T17:09:54.952097Z","submitted_at":"2024-11-17T18:25:01Z","title":"CLMIA: Membership Inference Attacks via Unsupervised Contrastive Learning","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-12T18:54:57.819552Z"},"links":{"citing_paper":"/paper/2411.11144"},"observation_digest":"sha256:338ecf33e9c392dfa1acbcf9f4e48d8fbd300993bee9e1da783e479f6cdc6aec","observation_id":"be0123c1-519c-418b-96eb-f03f19f44c66","resolution":{"observed_at":"2026-08-12T18:54:58.056129Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2411.11144","last_updated":"2024-11-17T18:25:01Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-19T17:09:54.952097Z","submitted_at":"2024-11-17T18:25:01Z","title":"CLMIA: Membership Inference Attacks via Unsupervised Contrastive Learning"},"reference_resolution":{"displayed":43,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":17,"verified_exact":1,"verified_fuzzy":25},"total_outbound_references":43},"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":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"thesis":"As of 20 August 2026, this Paper Citation Record lists 43 of 43 outbound references and 0 inbound Pith citation observations for arXiv:2411.11144."}