{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:UROLBPRNUZW6CVGNWAHNMVMHH5","short_pith_number":"pith:UROLBPRN","schema_version":"1.0","canonical_sha256":"a45cb0be2da66de154cdb00ed655873f7793a8f621b790cf86fc2831155359bd","source":{"kind":"arxiv","id":"2407.07403","version":2},"attestation_state":"computed","paper":{"title":"A Survey of Attacks on Large Vision-Language Models: Resources, Advances, and Future Trends","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Daizong Liu, Mingyu Yang, Pan Zhou, Wei Hu, Xiaoye Qu, Yu Cheng","submitted_at":"2024-07-10T06:57:58Z","abstract_excerpt":"With the significant development of large models in recent years, Large Vision-Language Models (LVLMs) have demonstrated remarkable capabilities across a wide range of multimodal understanding and reasoning tasks. Compared to traditional Large Language Models (LLMs), LVLMs present great potential and challenges due to its closer proximity to the multi-resource real-world applications and the complexity of multi-modal processing. However, the vulnerability of LVLMs is relatively underexplored, posing potential security risks in daily usage. In this paper, we provide a comprehensive review of th"},"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":"2407.07403","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-07-10T06:57:58Z","cross_cats_sorted":[],"title_canon_sha256":"44cabaadc30e8e94081f5128ff989aaa4b54e518a93970894cba5ce3ed454b50","abstract_canon_sha256":"f6e178b8a75f6b7e39a2b9c9b849c8ef1ac29e1d0be5334fe086e9479dc5f80b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:42:55.292889Z","signature_b64":"E67kM+4QlEL2agDt9XjqqFzJHT8GW7d+4F43WBX21Ygn1+0v/hYOFDFFEJ5fc5cY5JYeSr7mCX1yYpj6qpVkBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a45cb0be2da66de154cdb00ed655873f7793a8f621b790cf86fc2831155359bd","last_reissued_at":"2026-07-05T08:42:55.292456Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:42:55.292456Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Survey of Attacks on Large Vision-Language Models: Resources, Advances, and Future Trends","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Daizong Liu, Mingyu Yang, Pan Zhou, Wei Hu, Xiaoye Qu, Yu Cheng","submitted_at":"2024-07-10T06:57:58Z","abstract_excerpt":"With the significant development of large models in recent years, Large Vision-Language Models (LVLMs) have demonstrated remarkable capabilities across a wide range of multimodal understanding and reasoning tasks. Compared to traditional Large Language Models (LLMs), LVLMs present great potential and challenges due to its closer proximity to the multi-resource real-world applications and the complexity of multi-modal processing. However, the vulnerability of LVLMs is relatively underexplored, posing potential security risks in daily usage. In this paper, we provide a comprehensive review of th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.07403","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/2407.07403/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":"2407.07403","created_at":"2026-07-05T08:42:55.292516+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.07403v2","created_at":"2026-07-05T08:42:55.292516+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.07403","created_at":"2026-07-05T08:42:55.292516+00:00"},{"alias_kind":"pith_short_12","alias_value":"UROLBPRNUZW6","created_at":"2026-07-05T08:42:55.292516+00:00"},{"alias_kind":"pith_short_16","alias_value":"UROLBPRNUZW6CVGN","created_at":"2026-07-05T08:42:55.292516+00:00"},{"alias_kind":"pith_short_8","alias_value":"UROLBPRN","created_at":"2026-07-05T08:42:55.292516+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":8,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.25194","citing_title":"Localization then Neutralization: Gradient-guided Token Suppression against Visual Prompt Injection Attack","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2409.18169","citing_title":"Harmful Fine-tuning Attacks and Defenses for Large Language Models: A Survey","ref_index":95,"is_internal_anchor":false},{"citing_arxiv_id":"2412.00404","citing_title":"Hard-Label Black-Box Attacks on 3D Point Clouds","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2503.06223","citing_title":"RedDiffuser: Auditing Multimodal Safety Failures in Vision-Language Models via Reinforced Diffusion","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2509.15435","citing_title":"ORCA: An Agentic Reasoning Framework for Hallucination and Adversarial Robustness in Vision-Language Models","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2509.15435","citing_title":"ORCA: An Agentic Reasoning Framework for Hallucination and Adversarial Robustness in Vision-Language Models","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14291","citing_title":"To See is Not to Learn: Protecting Multimodal Data from Unauthorized Fine-Tuning of Large Vision-Language Model","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2604.02689","citing_title":"Efficient3D: A Unified Framework for Adaptive and Debiased Token Reduction in 3D MLLMs","ref_index":47,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UROLBPRNUZW6CVGNWAHNMVMHH5","json":"https://pith.science/pith/UROLBPRNUZW6CVGNWAHNMVMHH5.json","graph_json":"https://pith.science/api/pith-number/UROLBPRNUZW6CVGNWAHNMVMHH5/graph.json","events_json":"https://pith.science/api/pith-number/UROLBPRNUZW6CVGNWAHNMVMHH5/events.json","paper":"https://pith.science/paper/UROLBPRN"},"agent_actions":{"view_html":"https://pith.science/pith/UROLBPRNUZW6CVGNWAHNMVMHH5","download_json":"https://pith.science/pith/UROLBPRNUZW6CVGNWAHNMVMHH5.json","view_paper":"https://pith.science/paper/UROLBPRN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.07403&json=true","fetch_graph":"https://pith.science/api/pith-number/UROLBPRNUZW6CVGNWAHNMVMHH5/graph.json","fetch_events":"https://pith.science/api/pith-number/UROLBPRNUZW6CVGNWAHNMVMHH5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UROLBPRNUZW6CVGNWAHNMVMHH5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UROLBPRNUZW6CVGNWAHNMVMHH5/action/storage_attestation","attest_author":"https://pith.science/pith/UROLBPRNUZW6CVGNWAHNMVMHH5/action/author_attestation","sign_citation":"https://pith.science/pith/UROLBPRNUZW6CVGNWAHNMVMHH5/action/citation_signature","submit_replication":"https://pith.science/pith/UROLBPRNUZW6CVGNWAHNMVMHH5/action/replication_record"}},"created_at":"2026-07-05T08:42:55.292516+00:00","updated_at":"2026-07-05T08:42:55.292516+00:00"}