{"as_of":"2026-08-11T17:46:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:cc799ace87ccc7e3aeddcbcfc22db971f259caa3809e5446f5d41d3d668f7872","coverage":[{"denominator":34,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":34,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-10T20:32:52.893236Z","state":"measured"},{"denominator":34,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":34,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-11T06:34:44.6726+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/2501.08152/citation-record","integrity":"/paper/2501.08152/integrity","json":"/paper/2501.08152/citation-record.json","paper":"/paper/2501.08152"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T20:32:53.456194Z","title":"Going deeper with convolutions,","venue":null,"work_id":"9f0cf129-f27a-485b-be6a-3a36bfa87cde","year":2015},"citing_paper":{"arxiv_id":"2501.08152","last_updated":"2025-01-14T14:26:18Z","snapshot_observed_at":"2026-08-11T09:45:10.315500Z","submitted_at":"2025-01-14T14:26:18Z","title":"Energy Backdoor Attack to Deep Neural Networks","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-10T20:32:52.774995Z"},"links":{"citing_paper":"/paper/2501.08152"},"observation_digest":"sha256:55531515aa48f63db11c33e3530ee3e272d2e3983979d7535b6a9482175e965b","observation_id":"d0ccd4a5-fcaa-4894-b4d1-8bea1ee4c3e9","resolution":{"observed_at":"2026-08-10T20:32:53.460082Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T20:32:53.445196Z","title":"Hardware implementation of deep network accelerators towards healthcare and biomedical applications,","venue":null,"work_id":"2bf96d4a-8a8c-4a8b-acb8-6e829d84a485","year":2020},"citing_paper":{"arxiv_id":"2501.08152","last_updated":"2025-01-14T14:26:18Z","snapshot_observed_at":"2026-08-11T09:45:10.315500Z","submitted_at":"2025-01-14T14:26:18Z","title":"Energy Backdoor Attack to Deep Neural Networks","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-10T20:32:52.779062Z"},"links":{"citing_paper":"/paper/2501.08152"},"observation_digest":"sha256:1478bf26689ad319dc00f12d828000059be27394b6b78edb5d80327604fe4986","observation_id":"b406ccbe-a245-4a69-a04b-8cac74148d08","resolution":{"observed_at":"2026-08-10T20:32:53.449095Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T20:32:53.433254Z","title":"Scnn: An accelerator for compressed-sparse convolutional neural networks,","venue":null,"work_id":"8c7cdb99-3bcc-48e4-b2df-b2531eb6bc9e","year":2017},"citing_paper":{"arxiv_id":"2501.08152","last_updated":"2025-01-14T14:26:18Z","snapshot_observed_at":"2026-08-11T09:45:10.315500Z","submitted_at":"2025-01-14T14:26:18Z","title":"Energy Backdoor Attack to Deep Neural Networks","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-10T20:32:52.782745Z"},"links":{"citing_paper":"/paper/2501.08152"},"observation_digest":"sha256:f302bdc1cb7d281471f855359545d1f51c40d64e11b5205657c18f15c021444e","observation_id":"9172e426-94c1-4242-9444-4e6c7d6b6723","resolution":{"observed_at":"2026-08-10T20:32:53.438817Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2203.08147","last_updated":"2025-04-18T12:28:58Z","snapshot_observed_at":"2026-07-06T12:48:16.632982Z","submitted_at":"2022-03-14T17:18:10Z","title":"Energy-Latency Attacks via Sponge Poisoning","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2203.08147","snapshot_observed_at":"2026-08-10T20:32:52.786315Z","title":"Energy-latency attacks via sponge poisoning,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2501.08152","last_updated":"2025-01-14T14:26:18Z","snapshot_observed_at":"2026-08-11T09:45:10.315500Z","submitted_at":"2025-01-14T14:26:18Z","title":"Energy Backdoor Attack to Deep Neural Networks","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-10T20:32:52.786315Z"},"links":{"cited_paper":"/paper/2203.08147","citing_paper":"/paper/2501.08152"},"observation_digest":"sha256:fdc53c51d4aae7fa6f8fa4317da7b6928d8874aa3333a72344cb6aa0bacedcad","observation_id":"522112cd-6eef-4a5d-91ea-c958a2c0876f","resolution":{"observed_at":"2026-08-10T20:32:52.786315Z","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":"2026-08-10T20:32:53.421346Z","title":"Sponge examples: Energy-latency attacks on neural networks,","venue":null,"work_id":"61914384-d3ef-4c81-bf64-99739316a63d","year":2021},"citing_paper":{"arxiv_id":"2501.08152","last_updated":"2025-01-14T14:26:18Z","snapshot_observed_at":"2026-08-11T09:45:10.315500Z","submitted_at":"2025-01-14T14:26:18Z","title":"Energy Backdoor Attack to Deep Neural Networks","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-10T20:32:52.790309Z"},"links":{"citing_paper":"/paper/2501.08152"},"observation_digest":"sha256:ca51e07abde3ab1be271b3818349a87aceeeae56a0eb0a83ec290041f70a8b90","observation_id":"ccfd7354-0d2f-45a0-aebb-b433fc947572","resolution":{"observed_at":"2026-08-10T20:32:53.425890Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T20:32:53.410404Z","title":"The dark side of dynamic routing neural networks: Towards efficiency backdoor injection,","venue":null,"work_id":"a0b7cd73-9e1a-4473-9749-0af2eaac3ae9","year":2023},"citing_paper":{"arxiv_id":"2501.08152","last_updated":"2025-01-14T14:26:18Z","snapshot_observed_at":"2026-08-11T09:45:10.315500Z","submitted_at":"2025-01-14T14:26:18Z","title":"Energy Backdoor Attack to Deep Neural Networks","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-10T20:32:52.793854Z"},"links":{"citing_paper":"/paper/2501.08152"},"observation_digest":"sha256:d8afdd680918ffdfb0c0ea85f3fa52215e0d51cb416249e9699b84d057f43c1a","observation_id":"0092c3ff-7341-4c28-9622-39370a3043b9","resolution":{"observed_at":"2026-08-10T20:32:53.414134Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2310.02544","last_updated":"2023-10-04T02:57:01Z","snapshot_observed_at":"2026-07-06T16:27:26.971077Z","submitted_at":"2023-10-04T02:57:01Z","title":"SlowFormer: Universal Adversarial Patch for Attack on Compute and Energy Efficiency of Inference Efficient Vision Transformers","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.02544","snapshot_observed_at":"2026-08-10T20:32:52.797767Z","title":"Slowformer: Universal adversarial patch for attack on compute and energy efficiency of inference efficient vision trans- formers,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2501.08152","last_updated":"2025-01-14T14:26:18Z","snapshot_observed_at":"2026-08-11T09:45:10.315500Z","submitted_at":"2025-01-14T14:26:18Z","title":"Energy Backdoor Attack to Deep Neural Networks","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-10T20:32:52.797767Z"},"links":{"cited_paper":"/paper/2310.02544","citing_paper":"/paper/2501.08152"},"observation_digest":"sha256:5314bd86e289955bb157f74a35a6f9dfd57734f2f38c9d9e87d07867caa239fb","observation_id":"2342505e-35f2-4771-b3ca-66d1e79dd2fc","resolution":{"observed_at":"2026-08-10T20:32:52.797767Z","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":"2026-08-10T20:32:53.400163Z","title":"Gradauto: Energy-oriented attack on dynamic neural networks,","venue":null,"work_id":"c06d73bc-0e2e-496d-ba9f-18cd54227791","year":2022},"citing_paper":{"arxiv_id":"2501.08152","last_updated":"2025-01-14T14:26:18Z","snapshot_observed_at":"2026-08-11T09:45:10.315500Z","submitted_at":"2025-01-14T14:26:18Z","title":"Energy Backdoor Attack to Deep Neural Networks","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-10T20:32:52.801624Z"},"links":{"citing_paper":"/paper/2501.08152"},"observation_digest":"sha256:c87b33dc746a50c99b3b1542a29dfdf9fc9d69fb812877c4c259824b40a02c36","observation_id":"4caac472-2e67-4e26-b996-907cea70fed9","resolution":{"observed_at":"2026-08-10T20:32:53.403727Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T20:32:53.390073Z","title":"Slowlidar: In- creasing the latency of lidar-based detection using adversarial examples,","venue":null,"work_id":"4bda6933-6a6d-4cab-94f8-4c0bbfa8134c","year":2023},"citing_paper":{"arxiv_id":"2501.08152","last_updated":"2025-01-14T14:26:18Z","snapshot_observed_at":"2026-08-11T09:45:10.315500Z","submitted_at":"2025-01-14T14:26:18Z","title":"Energy Backdoor Attack to Deep Neural Networks","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-10T20:32:52.805124Z"},"links":{"citing_paper":"/paper/2501.08152"},"observation_digest":"sha256:37cb5d0717915682758f5aa97348cc73b85239b17354586f9a3d871ac55125ce","observation_id":"53d6d0bf-282b-4c08-a412-5814e3bb0bfc","resolution":{"observed_at":"2026-08-10T20:32:53.394018Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T20:32:53.379914Z","title":"Ereba: black-box energy testing of adaptive neural networks,","venue":null,"work_id":"fd0d1ed8-381a-47d4-9c4a-41a638bedce6","year":2022},"citing_paper":{"arxiv_id":"2501.08152","last_updated":"2025-01-14T14:26:18Z","snapshot_observed_at":"2026-08-11T09:45:10.315500Z","submitted_at":"2025-01-14T14:26:18Z","title":"Energy Backdoor Attack to Deep Neural Networks","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-10T20:32:52.808419Z"},"links":{"citing_paper":"/paper/2501.08152"},"observation_digest":"sha256:05033bd265e1a39b56250db0de29b7613be728dc96c3bdc86f01825747e7937f","observation_id":"d1fcb23d-76f0-4d20-b626-c75df234c836","resolution":{"observed_at":"2026-08-10T20:32:53.383778Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T20:32:53.369905Z","title":"Antinode: Evaluating efficiency robustness of neural odes,","venue":null,"work_id":"b1f5ef2c-0015-4e29-b199-627b9d1f6872","year":2023},"citing_paper":{"arxiv_id":"2501.08152","last_updated":"2025-01-14T14:26:18Z","snapshot_observed_at":"2026-08-11T09:45:10.315500Z","submitted_at":"2025-01-14T14:26:18Z","title":"Energy Backdoor Attack to Deep Neural Networks","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-10T20:32:52.811677Z"},"links":{"citing_paper":"/paper/2501.08152"},"observation_digest":"sha256:f4dd239ccaf917a5c3eba6cc4002f78f110376176b9e9b996fc7a077a3d698db","observation_id":"1a952295-a62d-4700-a6c4-2b5121a20485","resolution":{"observed_at":"2026-08-10T20:32:53.373382Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T20:32:52.815299Z","title":"The spongenet attack: Sponge weight poisoning of deep neural networks,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2501.08152","last_updated":"2025-01-14T14:26:18Z","snapshot_observed_at":"2026-08-11T09:45:10.315500Z","submitted_at":"2025-01-14T14:26:18Z","title":"Energy Backdoor Attack to Deep Neural Networks","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-10T20:32:52.815299Z"},"links":{"citing_paper":"/paper/2501.08152"},"observation_digest":"sha256:bc6a73bb07991fde95b7f08fb01207f01b327f4d2a937299b7691c76f3c88222","observation_id":"85b3a617-1d35-4ddf-aeab-e6693e8af1ca","resolution":{"observed_at":"2026-08-10T20:32:52.815299Z","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":"2026-08-10T20:32:53.358921Z","title":"Sparsity turns adversarial: Energy and latency attacks on deep neural networks,","venue":null,"work_id":"a58bd153-b1fb-462d-8801-5f1f20e8073e","year":2020},"citing_paper":{"arxiv_id":"2501.08152","last_updated":"2025-01-14T14:26:18Z","snapshot_observed_at":"2026-08-11T09:45:10.315500Z","submitted_at":"2025-01-14T14:26:18Z","title":"Energy Backdoor Attack to Deep Neural Networks","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-10T20:32:52.818489Z"},"links":{"citing_paper":"/paper/2501.08152"},"observation_digest":"sha256:a86dbbd236fe51a71e8d4982a8a18ab0678cef5e3506b9e76e0bacb9ac8cf855","observation_id":"ce972cde-e88a-4490-811c-df03460187c3","resolution":{"observed_at":"2026-08-10T20:32:53.363588Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T20:32:53.348299Z","title":"Sponge attack against multi-exit networks with data poisoning,","venue":null,"work_id":"f2baedab-b3ed-4148-a6d5-8af97e2d024c","year":2024},"citing_paper":{"arxiv_id":"2501.08152","last_updated":"2025-01-14T14:26:18Z","snapshot_observed_at":"2026-08-11T09:45:10.315500Z","submitted_at":"2025-01-14T14:26:18Z","title":"Energy Backdoor Attack to Deep Neural Networks","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-10T20:32:52.821854Z"},"links":{"citing_paper":"/paper/2501.08152"},"observation_digest":"sha256:cfc6688d581bddaf0f5527c691291350ead19c2f60c181daa19dd154d2751b01","observation_id":"bf6d3194-c533-4b50-943d-d34ef769008e","resolution":{"observed_at":"2026-08-10T20:32:53.352057Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T20:32:53.337499Z","title":"Effi- ciency attacks on spiking neural networks,","venue":null,"work_id":"4ff77020-6cf7-4d1a-bff7-0733f4720c90","year":2022},"citing_paper":{"arxiv_id":"2501.08152","last_updated":"2025-01-14T14:26:18Z","snapshot_observed_at":"2026-08-11T09:45:10.315500Z","submitted_at":"2025-01-14T14:26:18Z","title":"Energy Backdoor Attack to Deep Neural Networks","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-10T20:32:52.825670Z"},"links":{"citing_paper":"/paper/2501.08152"},"observation_digest":"sha256:04602ed46b2eea174d7d60af29ec15923de1717338b1d7e997e984d13a20542a","observation_id":"67283f61-25d2-46be-adaf-8f73d960ea75","resolution":{"observed_at":"2026-08-10T20:32:53.341564Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T20:32:53.326308Z","title":"Nicgslowdown: Evaluating the efficiency robustness of neural image caption generation models,","venue":null,"work_id":"d4eb8984-58c4-42c2-b2f5-3878c47600d9","year":2022},"citing_paper":{"arxiv_id":"2501.08152","last_updated":"2025-01-14T14:26:18Z","snapshot_observed_at":"2026-08-11T09:45:10.315500Z","submitted_at":"2025-01-14T14:26:18Z","title":"Energy Backdoor Attack to Deep Neural Networks","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-10T20:32:52.829253Z"},"links":{"citing_paper":"/paper/2501.08152"},"observation_digest":"sha256:9704efa936c177839198ce2d8000e802a9a97a52638f3cc07e8a39d54b3fcf3c","observation_id":"b8cbe60e-090d-4f7d-a798-03de534544ef","resolution":{"observed_at":"2026-08-10T20:32:53.330737Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T20:32:53.316458Z","title":"Energy- latency attacks to on-device neural networks via sponge poisoning,","venue":null,"work_id":"0dcef786-f20c-4839-b943-4553108cc5c7","year":2023},"citing_paper":{"arxiv_id":"2501.08152","last_updated":"2025-01-14T14:26:18Z","snapshot_observed_at":"2026-08-11T09:45:10.315500Z","submitted_at":"2025-01-14T14:26:18Z","title":"Energy Backdoor Attack to Deep Neural Networks","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-10T20:32:52.832621Z"},"links":{"citing_paper":"/paper/2501.08152"},"observation_digest":"sha256:4b212b90a1d0c73610b584704e65d59c3c778f962f761ddb213223f7e26cb92a","observation_id":"04517019-7d3c-4e88-93a9-cff63efbae47","resolution":{"observed_at":"2026-08-10T20:32:53.320038Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2403.18587","last_updated":"2024-03-27T14:11:23Z","snapshot_observed_at":"2026-08-11T15:08:15.378880Z","submitted_at":"2024-03-27T14:11:23Z","title":"The Impact of Uniform Inputs on Activation Sparsity and Energy-Latency Attacks in Computer Vision","version":1},"cited_work":{"arxiv_id":"2403.18587","doi":null,"metadata_source":"pith","pith_arxiv_id":"2403.18587","snapshot_observed_at":"2026-08-10T20:32:52.952227Z","title":"The Impact of Uniform Inputs on Activation Sparsity and Energy-Latency Attacks in Computer Vision","venue":"cs.CR","work_id":"4d0c3a23-9f3f-4fdc-a7a2-e79213d61c0b","year":2024},"citing_paper":{"arxiv_id":"2501.08152","last_updated":"2025-01-14T14:26:18Z","snapshot_observed_at":"2026-08-11T09:45:10.315500Z","submitted_at":"2025-01-14T14:26:18Z","title":"Energy Backdoor Attack to Deep Neural Networks","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-10T20:32:52.836471Z"},"links":{"cited_paper":"/paper/2403.18587","citing_paper":"/paper/2501.08152"},"observation_digest":"sha256:4d2b94425bfa30c1a68c8757761bf277f2a8876e93f1e0e794f3cd8d738396ea","observation_id":"588ca9bb-f98e-4e1f-814d-f5506e3f7d99","resolution":{"observed_at":"2026-08-10T20:32:52.958100Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T20:32:53.306568Z","title":"Trojaning attack on neural networks,","venue":null,"work_id":"b23beb31-55e8-4c48-879a-3673abace8be","year":2017},"citing_paper":{"arxiv_id":"2501.08152","last_updated":"2025-01-14T14:26:18Z","snapshot_observed_at":"2026-08-11T09:45:10.315500Z","submitted_at":"2025-01-14T14:26:18Z","title":"Energy Backdoor Attack to Deep Neural Networks","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-10T20:32:52.841077Z"},"links":{"citing_paper":"/paper/2501.08152"},"observation_digest":"sha256:3b47934672a19b4359496bf7b7b78cdcea56ef65e596b085bd10506e2846c7ab","observation_id":"4d756e6e-f740-46b2-ab13-3326e65b22a8","resolution":{"observed_at":"2026-08-10T20:32:53.310406Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T20:32:53.296713Z","title":"Reflection backdoor: A natural backdoor attack on deep neural networks,","venue":null,"work_id":"ef7ff48d-14af-4711-863d-73fa962f3d3d","year":2020},"citing_paper":{"arxiv_id":"2501.08152","last_updated":"2025-01-14T14:26:18Z","snapshot_observed_at":"2026-08-11T09:45:10.315500Z","submitted_at":"2025-01-14T14:26:18Z","title":"Energy Backdoor Attack to Deep Neural Networks","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-10T20:32:52.844626Z"},"links":{"citing_paper":"/paper/2501.08152"},"observation_digest":"sha256:d790b468c3adc187c32ddcc1816fee890091b1ceefa53c2b6877a5dab36728bd","observation_id":"20b59129-c300-4cf2-a027-596bd50521f7","resolution":{"observed_at":"2026-08-10T20:32:53.300295Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T20:32:53.286570Z","title":"Backdoor attacks against deep image compression via adaptive frequency trigger,","venue":null,"work_id":"7262dd24-93c6-435e-985e-d155d69bdb1a","year":2023},"citing_paper":{"arxiv_id":"2501.08152","last_updated":"2025-01-14T14:26:18Z","snapshot_observed_at":"2026-08-11T09:45:10.315500Z","submitted_at":"2025-01-14T14:26:18Z","title":"Energy Backdoor Attack to Deep Neural Networks","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-10T20:32:52.847895Z"},"links":{"citing_paper":"/paper/2501.08152"},"observation_digest":"sha256:ea7eb1812b7e1f210c05e9eceb08e61b7b7db8cd89014604bae4ac2a5128e0ac","observation_id":"332db1cd-2f78-44ad-9569-f94cd05c08b3","resolution":{"observed_at":"2026-08-10T20:32:53.290471Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T20:32:53.276556Z","title":"Luminance-based video backdoor attack against anti-spoofing rebroad- cast detection,","venue":null,"work_id":"40246208-f143-44e0-a4f2-3e2b082b5b64","year":2019},"citing_paper":{"arxiv_id":"2501.08152","last_updated":"2025-01-14T14:26:18Z","snapshot_observed_at":"2026-08-11T09:45:10.315500Z","submitted_at":"2025-01-14T14:26:18Z","title":"Energy Backdoor Attack to Deep Neural Networks","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-10T20:32:52.851219Z"},"links":{"citing_paper":"/paper/2501.08152"},"observation_digest":"sha256:b561a1c290d8f1f80a8c4782dd6d9130c786e2296c232390961f7bab94951bb3","observation_id":"806cc70a-04e0-40df-b4db-f102849a5a52","resolution":{"observed_at":"2026-08-10T20:32:53.280166Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T20:32:53.266287Z","title":"On the lasso and its dual,","venue":null,"work_id":"d618fdec-a93f-4e9f-8df6-79037da788f0","year":2000},"citing_paper":{"arxiv_id":"2501.08152","last_updated":"2025-01-14T14:26:18Z","snapshot_observed_at":"2026-08-11T09:45:10.315500Z","submitted_at":"2025-01-14T14:26:18Z","title":"Energy Backdoor Attack to Deep Neural Networks","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-10T20:32:52.854487Z"},"links":{"citing_paper":"/paper/2501.08152"},"observation_digest":"sha256:8d2891a5da3dde36ba8dc2f8722612d2b726638894364aab9c2e162e61666704","observation_id":"77394af6-f729-4e95-872d-d292cbd3ade2","resolution":{"observed_at":"2026-08-10T20:32:53.269947Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T20:32:53.254307Z","title":"Fiba: Federated invisible backdoor attack,","venue":null,"work_id":"c0175410-1956-41de-8cfd-96d6f4a06380","year":2024},"citing_paper":{"arxiv_id":"2501.08152","last_updated":"2025-01-14T14:26:18Z","snapshot_observed_at":"2026-08-11T09:45:10.315500Z","submitted_at":"2025-01-14T14:26:18Z","title":"Energy Backdoor Attack to Deep Neural Networks","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-10T20:32:52.857811Z"},"links":{"citing_paper":"/paper/2501.08152"},"observation_digest":"sha256:d05f94d4b0164b2e3af6487cfa3c167ecb460f14c1b94e5703102da73bd390c9","observation_id":"8b79d769-889c-4ed3-a80b-f127dbe2a24b","resolution":{"observed_at":"2026-08-10T20:32:53.258900Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T20:32:53.242804Z","title":"Invisible backdoor attacks on deep neural networks via steganography and regularization,","venue":null,"work_id":"cd20103b-d5d5-4b37-a188-b98733909bd3","year":2020},"citing_paper":{"arxiv_id":"2501.08152","last_updated":"2025-01-14T14:26:18Z","snapshot_observed_at":"2026-08-11T09:45:10.315500Z","submitted_at":"2025-01-14T14:26:18Z","title":"Energy Backdoor Attack to Deep Neural Networks","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-10T20:32:52.861092Z"},"links":{"citing_paper":"/paper/2501.08152"},"observation_digest":"sha256:a719dab22c77e6cb38ea5ac5753f694da1707771495b424a1b1d036a1a07b90d","observation_id":"68d58224-d11a-4b57-886e-0b81d18d2901","resolution":{"observed_at":"2026-08-10T20:32:53.246879Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T20:32:53.231548Z","title":"Backdoor attack with sparse and invisible trigger,","venue":null,"work_id":"2d2639a1-748a-49ea-80f7-ababe488738b","year":2024},"citing_paper":{"arxiv_id":"2501.08152","last_updated":"2025-01-14T14:26:18Z","snapshot_observed_at":"2026-08-11T09:45:10.315500Z","submitted_at":"2025-01-14T14:26:18Z","title":"Energy Backdoor Attack to Deep Neural Networks","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-10T20:32:52.864150Z"},"links":{"citing_paper":"/paper/2501.08152"},"observation_digest":"sha256:7904b8a45e17a369abe6bd83eef8f3107ec34e90995764243e4c4685fcbd2127","observation_id":"68f9bd0b-8358-4da4-b6c9-5bbb1bc58d66","resolution":{"observed_at":"2026-08-10T20:32:53.235389Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T20:32:53.118660Z","title":"Poison frogs! targeted clean-label poisoning attacks on neural networks,","venue":null,"work_id":"386baa82-ed5d-44c0-957d-5cf8f8edd290","year":2018},"citing_paper":{"arxiv_id":"2501.08152","last_updated":"2025-01-14T14:26:18Z","snapshot_observed_at":"2026-08-11T09:45:10.315500Z","submitted_at":"2025-01-14T14:26:18Z","title":"Energy Backdoor Attack to Deep Neural Networks","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-10T20:32:52.867587Z"},"links":{"citing_paper":"/paper/2501.08152"},"observation_digest":"sha256:7017edd2c381fa490355cd440ad08bb7769b4722d5f5bfd35b192a8100a0283d","observation_id":"edab9eb8-3d4a-4ecd-a5bd-32ba02e2e4e0","resolution":{"observed_at":"2026-08-10T20:32:53.122748Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T20:32:53.106792Z","title":"An overview of backdoor attacks against deep neural networks and possible defences,","venue":null,"work_id":"ac9c819c-144b-4655-a89e-2cd691a0c3f7","year":2022},"citing_paper":{"arxiv_id":"2501.08152","last_updated":"2025-01-14T14:26:18Z","snapshot_observed_at":"2026-08-11T09:45:10.315500Z","submitted_at":"2025-01-14T14:26:18Z","title":"Energy Backdoor Attack to Deep Neural Networks","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-10T20:32:52.871958Z"},"links":{"citing_paper":"/paper/2501.08152"},"observation_digest":"sha256:1438d40e8b09b0813456595d68cc38a8daf9ca7351e3161b349892b32e93b61c","observation_id":"b2bc12fb-444a-4129-95af-bc6e2f5eefaf","resolution":{"observed_at":"2026-08-10T20:32:53.110609Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T20:32:53.095080Z","title":"Learning multiple layers of features from tiny images.(2009),","venue":null,"work_id":"7099f249-3804-4ffa-b35d-b33ace2c3473","year":2009},"citing_paper":{"arxiv_id":"2501.08152","last_updated":"2025-01-14T14:26:18Z","snapshot_observed_at":"2026-08-11T09:45:10.315500Z","submitted_at":"2025-01-14T14:26:18Z","title":"Energy Backdoor Attack to Deep Neural Networks","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-10T20:32:52.875452Z"},"links":{"citing_paper":"/paper/2501.08152"},"observation_digest":"sha256:243f5690c8b521384b14665e419db77026b0c80881bf1f2f9e5bae2ded81fe38","observation_id":"3698cdf8-49c3-407b-83b7-d79c61255014","resolution":{"observed_at":"2026-08-10T20:32:53.099875Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2007.06712","last_updated":"2020-06-19T15:49:39Z","snapshot_observed_at":"2026-08-10T13:44:55.724851Z","submitted_at":"2020-06-19T15:49:39Z","title":"Embedded Encoder-Decoder in Convolutional Networks Towards Explainable AI","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2007.06712","snapshot_observed_at":"2026-08-10T20:32:52.879287Z","title":"Embedded encoder-decoder in convolutional networks towards explainable ai,","venue":null,"work_id":null,"year":2007},"citing_paper":{"arxiv_id":"2501.08152","last_updated":"2025-01-14T14:26:18Z","snapshot_observed_at":"2026-08-11T09:45:10.315500Z","submitted_at":"2025-01-14T14:26:18Z","title":"Energy Backdoor Attack to Deep Neural Networks","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-10T20:32:52.879287Z"},"links":{"cited_paper":"/paper/2007.06712","citing_paper":"/paper/2501.08152"},"observation_digest":"sha256:a4ea1f01eebfe9a6e50cf59554d5d4e37cd3120dd7407951806d0bc286c5283c","observation_id":"0908ef13-b06d-4697-81e0-151dc5b1f3ff","resolution":{"observed_at":"2026-08-10T20:32:52.879287Z","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":"2026-08-10T20:32:52.882974Z","title":"Deep residual learning for image recognition,","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2501.08152","last_updated":"2025-01-14T14:26:18Z","snapshot_observed_at":"2026-08-11T09:45:10.315500Z","submitted_at":"2025-01-14T14:26:18Z","title":"Energy Backdoor Attack to Deep Neural Networks","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-10T20:32:52.882974Z"},"links":{"citing_paper":"/paper/2501.08152"},"observation_digest":"sha256:f4ddf2250f58e8e131dd3cd54bdd7ea46620bbdbd80bf5719c64d326e1413d5b","observation_id":"951c879a-368d-4fc5-86be-2ed2a7e3f223","resolution":{"observed_at":"2026-08-10T20:32:52.882974Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1704.04861","last_updated":"2017-04-17T03:57:34Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2017-04-17T03:57:34Z","title":"MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1704.04861","snapshot_observed_at":"2026-08-10T20:32:52.886238Z","title":"Mobilenets: Efficient convolutional neural net- works for mobile vision applications,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2501.08152","last_updated":"2025-01-14T14:26:18Z","snapshot_observed_at":"2026-08-11T09:45:10.315500Z","submitted_at":"2025-01-14T14:26:18Z","title":"Energy Backdoor Attack to Deep Neural Networks","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-10T20:32:52.886238Z"},"links":{"cited_paper":"/paper/1704.04861","citing_paper":"/paper/2501.08152"},"observation_digest":"sha256:2ead8d2bc520ec1047da549d39da8fde85be7e94246f75a84f7a462ee567c06b","observation_id":"4a26a57b-4fc0-4009-b5a9-67617fda5dd6","resolution":{"observed_at":"2026-08-10T20:32:52.886238Z","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":"2026-08-10T20:32:53.078187Z","title":"A new backdoor attack in cnns by training set corruption without label poisoning,","venue":null,"work_id":"929a81cd-4f31-4cf1-9724-1b221683ca0c","year":2019},"citing_paper":{"arxiv_id":"2501.08152","last_updated":"2025-01-14T14:26:18Z","snapshot_observed_at":"2026-08-11T09:45:10.315500Z","submitted_at":"2025-01-14T14:26:18Z","title":"Energy Backdoor Attack to Deep Neural Networks","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-10T20:32:52.889947Z"},"links":{"citing_paper":"/paper/2501.08152"},"observation_digest":"sha256:276c9f94499decad6f0f6720902e4e454eefc9b410231edb6b933e5147cbab8b","observation_id":"bfbd6da2-4c47-4cb2-9a3e-12b236a64031","resolution":{"observed_at":"2026-08-10T20:32:53.082143Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1606.01885","last_updated":"2016-06-06T19:50:47Z","snapshot_observed_at":"2026-08-09T05:53:23.612940Z","submitted_at":"2016-06-06T19:50:47Z","title":"Learning to Optimize","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1606.01885","snapshot_observed_at":"2026-08-10T20:32:52.893236Z","title":"Learning to optimize,","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2501.08152","last_updated":"2025-01-14T14:26:18Z","snapshot_observed_at":"2026-08-11T09:45:10.315500Z","submitted_at":"2025-01-14T14:26:18Z","title":"Energy Backdoor Attack to Deep Neural Networks","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-10T20:32:52.893236Z"},"links":{"cited_paper":"/paper/1606.01885","citing_paper":"/paper/2501.08152"},"observation_digest":"sha256:2da5f526f4c0e4b183b1d02d4b6c599d574c87a56a50f982cecfc29efea59b0d","observation_id":"376381f5-8e96-4864-9a96-aba8226edae1","resolution":{"observed_at":"2026-08-10T20:32:52.893236Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2501.08152","last_updated":"2025-01-14T14:26:18Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-11T09:45:10.315500Z","submitted_at":"2025-01-14T14:26:18Z","title":"Energy Backdoor Attack to Deep Neural Networks"},"reference_resolution":{"displayed":34,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":7,"verified_exact":1,"verified_fuzzy":26},"total_outbound_references":34},"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":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"thesis":"As of 11 August 2026, this Paper Citation Record lists 34 of 34 outbound references and 0 inbound Pith citation observations for arXiv:2501.08152."}