{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:XYCS6ZYJKZFNGC7RJM4HBMEI5V","short_pith_number":"pith:XYCS6ZYJ","schema_version":"1.0","canonical_sha256":"be052f6709564ad30bf14b3870b088ed6960de9cdfe83b97d4d57941000ab442","source":{"kind":"arxiv","id":"2508.02987","version":1},"attestation_state":"computed","paper":{"title":"Adversarial Attention Perturbations for Large Object Detection Transformers","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fatih Ilhan, Ling Liu, Margaret Loper, Selim Furkan Tekin, Sihao Hu, Tiansheng Huang, Yichang Xu, Zachary Yahn","submitted_at":"2025-08-05T01:31:10Z","abstract_excerpt":"Adversarial perturbations are useful tools for exposing vulnerabilities in neural networks. Existing adversarial perturbation methods for object detection are either limited to attacking CNN-based detectors or weak against transformer-based detectors. This paper presents an Attention-Focused Offensive Gradient (AFOG) attack against object detection transformers. By design, AFOG is neural-architecture agnostic and effective for attacking both large transformer-based object detectors and conventional CNN-based detectors with a unified adversarial attention framework. This paper makes three origi"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2508.02987","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-08-05T01:31:10Z","cross_cats_sorted":[],"title_canon_sha256":"158c6e5a4369229f07ea3717f2b6dde3891fd5cace4ae6d7fe3ad5568967a586","abstract_canon_sha256":"f1296f7e9568fdf0fe0fbdbd3a791e3a354a207e8a89417acd581c8a22c407ed"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:48:34.224243Z","signature_b64":"0ybLCBQ0FCts86J1788L+7Tv47G3EfAr2vVbd8goYBTXoMBN6O7XWvXKMvOjnUtujLAhSLJMD2ic/J2Mc+A2AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"be052f6709564ad30bf14b3870b088ed6960de9cdfe83b97d4d57941000ab442","last_reissued_at":"2026-07-05T11:48:34.223635Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:48:34.223635Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Adversarial Attention Perturbations for Large Object Detection Transformers","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fatih Ilhan, Ling Liu, Margaret Loper, Selim Furkan Tekin, Sihao Hu, Tiansheng Huang, Yichang Xu, Zachary Yahn","submitted_at":"2025-08-05T01:31:10Z","abstract_excerpt":"Adversarial perturbations are useful tools for exposing vulnerabilities in neural networks. Existing adversarial perturbation methods for object detection are either limited to attacking CNN-based detectors or weak against transformer-based detectors. This paper presents an Attention-Focused Offensive Gradient (AFOG) attack against object detection transformers. By design, AFOG is neural-architecture agnostic and effective for attacking both large transformer-based object detectors and conventional CNN-based detectors with a unified adversarial attention framework. This paper makes three origi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.02987","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2508.02987/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2508.02987","created_at":"2026-07-05T11:48:34.223707+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.02987v1","created_at":"2026-07-05T11:48:34.223707+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.02987","created_at":"2026-07-05T11:48:34.223707+00:00"},{"alias_kind":"pith_short_12","alias_value":"XYCS6ZYJKZFN","created_at":"2026-07-05T11:48:34.223707+00:00"},{"alias_kind":"pith_short_16","alias_value":"XYCS6ZYJKZFNGC7R","created_at":"2026-07-05T11:48:34.223707+00:00"},{"alias_kind":"pith_short_8","alias_value":"XYCS6ZYJ","created_at":"2026-07-05T11:48:34.223707+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2512.03730","citing_title":"Out-of-the-box: Black-box Causal Attacks on Object Detectors","ref_index":49,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XYCS6ZYJKZFNGC7RJM4HBMEI5V","json":"https://pith.science/pith/XYCS6ZYJKZFNGC7RJM4HBMEI5V.json","graph_json":"https://pith.science/api/pith-number/XYCS6ZYJKZFNGC7RJM4HBMEI5V/graph.json","events_json":"https://pith.science/api/pith-number/XYCS6ZYJKZFNGC7RJM4HBMEI5V/events.json","paper":"https://pith.science/paper/XYCS6ZYJ"},"agent_actions":{"view_html":"https://pith.science/pith/XYCS6ZYJKZFNGC7RJM4HBMEI5V","download_json":"https://pith.science/pith/XYCS6ZYJKZFNGC7RJM4HBMEI5V.json","view_paper":"https://pith.science/paper/XYCS6ZYJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.02987&json=true","fetch_graph":"https://pith.science/api/pith-number/XYCS6ZYJKZFNGC7RJM4HBMEI5V/graph.json","fetch_events":"https://pith.science/api/pith-number/XYCS6ZYJKZFNGC7RJM4HBMEI5V/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XYCS6ZYJKZFNGC7RJM4HBMEI5V/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XYCS6ZYJKZFNGC7RJM4HBMEI5V/action/storage_attestation","attest_author":"https://pith.science/pith/XYCS6ZYJKZFNGC7RJM4HBMEI5V/action/author_attestation","sign_citation":"https://pith.science/pith/XYCS6ZYJKZFNGC7RJM4HBMEI5V/action/citation_signature","submit_replication":"https://pith.science/pith/XYCS6ZYJKZFNGC7RJM4HBMEI5V/action/replication_record"}},"created_at":"2026-07-05T11:48:34.223707+00:00","updated_at":"2026-07-05T11:48:34.223707+00:00"}