{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:WYWIYITVCRTQRS6RZGXKYXS6Z5","short_pith_number":"pith:WYWIYITV","schema_version":"1.0","canonical_sha256":"b62c8c2275146708cbd1c9aeac5e5ecf6ef37f4d8b857342f556124f21dab567","source":{"kind":"arxiv","id":"2410.23687","version":2},"attestation_state":"computed","paper":{"title":"Adversarial Attacks of Vision Tasks in the Past 10 Years: A Survey","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR"],"primary_cat":"cs.CV","authors_text":"Chiyu Zhang, Jiafei Wu, Lu Zhou, Xiaogang Xu, Zhe Liu","submitted_at":"2024-10-31T07:22:51Z","abstract_excerpt":"With the advent of Large Vision-Language Models (LVLMs), new attack vectors, such as cognitive bias, prompt injection, and jailbreaking, have emerged. Understanding these attacks promotes system robustness improvement and neural networks demystification. However, existing surveys often target attack taxonomy and lack in-depth analysis like 1) unified insights into adversariality, transferability, and generalization; 2) detailed evaluations framework; 3) motivation-driven attack categorizations; and 4) an integrated perspective on both traditional and LVLM attacks. This article addresses these "},"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":"2410.23687","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-31T07:22:51Z","cross_cats_sorted":["cs.CR"],"title_canon_sha256":"5e076a8060a151e0fcd945d0b8f4407af8c046d5322cbc336df533cfe3d733e9","abstract_canon_sha256":"fa91abdc1a1b642d666883bbbc9a4976179454f72efba6efce1252add584d30f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:04:18.685012Z","signature_b64":"7YmYLVl0yv6ftxe2wie8XpxADHvI60GATpvs0Asx2uBnvTzBAxlxWBhMNdV2iwpOs1ITa4jMCmRVKx5s3y0CAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b62c8c2275146708cbd1c9aeac5e5ecf6ef37f4d8b857342f556124f21dab567","last_reissued_at":"2026-07-05T11:04:18.684525Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:04:18.684525Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Adversarial Attacks of Vision Tasks in the Past 10 Years: A Survey","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR"],"primary_cat":"cs.CV","authors_text":"Chiyu Zhang, Jiafei Wu, Lu Zhou, Xiaogang Xu, Zhe Liu","submitted_at":"2024-10-31T07:22:51Z","abstract_excerpt":"With the advent of Large Vision-Language Models (LVLMs), new attack vectors, such as cognitive bias, prompt injection, and jailbreaking, have emerged. Understanding these attacks promotes system robustness improvement and neural networks demystification. However, existing surveys often target attack taxonomy and lack in-depth analysis like 1) unified insights into adversariality, transferability, and generalization; 2) detailed evaluations framework; 3) motivation-driven attack categorizations; and 4) an integrated perspective on both traditional and LVLM attacks. This article addresses these "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.23687","kind":"arxiv","version":2},"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/2410.23687/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":"2410.23687","created_at":"2026-07-05T11:04:18.684588+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.23687v2","created_at":"2026-07-05T11:04:18.684588+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.23687","created_at":"2026-07-05T11:04:18.684588+00:00"},{"alias_kind":"pith_short_12","alias_value":"WYWIYITVCRTQ","created_at":"2026-07-05T11:04:18.684588+00:00"},{"alias_kind":"pith_short_16","alias_value":"WYWIYITVCRTQRS6R","created_at":"2026-07-05T11:04:18.684588+00:00"},{"alias_kind":"pith_short_8","alias_value":"WYWIYITV","created_at":"2026-07-05T11:04:18.684588+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.15720","citing_title":"Chain of Attack: On the Robustness of Vision-Language Models Against Transfer-Based Adversarial Attacks","ref_index":50,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WYWIYITVCRTQRS6RZGXKYXS6Z5","json":"https://pith.science/pith/WYWIYITVCRTQRS6RZGXKYXS6Z5.json","graph_json":"https://pith.science/api/pith-number/WYWIYITVCRTQRS6RZGXKYXS6Z5/graph.json","events_json":"https://pith.science/api/pith-number/WYWIYITVCRTQRS6RZGXKYXS6Z5/events.json","paper":"https://pith.science/paper/WYWIYITV"},"agent_actions":{"view_html":"https://pith.science/pith/WYWIYITVCRTQRS6RZGXKYXS6Z5","download_json":"https://pith.science/pith/WYWIYITVCRTQRS6RZGXKYXS6Z5.json","view_paper":"https://pith.science/paper/WYWIYITV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.23687&json=true","fetch_graph":"https://pith.science/api/pith-number/WYWIYITVCRTQRS6RZGXKYXS6Z5/graph.json","fetch_events":"https://pith.science/api/pith-number/WYWIYITVCRTQRS6RZGXKYXS6Z5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WYWIYITVCRTQRS6RZGXKYXS6Z5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WYWIYITVCRTQRS6RZGXKYXS6Z5/action/storage_attestation","attest_author":"https://pith.science/pith/WYWIYITVCRTQRS6RZGXKYXS6Z5/action/author_attestation","sign_citation":"https://pith.science/pith/WYWIYITVCRTQRS6RZGXKYXS6Z5/action/citation_signature","submit_replication":"https://pith.science/pith/WYWIYITVCRTQRS6RZGXKYXS6Z5/action/replication_record"}},"created_at":"2026-07-05T11:04:18.684588+00:00","updated_at":"2026-07-05T11:04:18.684588+00:00"}