{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:5HYQ7DC5QPYV2TUMJ5SGGDEVHC","short_pith_number":"pith:5HYQ7DC5","schema_version":"1.0","canonical_sha256":"e9f10f8c5d83f15d4e8c4f64630c9538949f9b27bf8384eff552d399f59b0703","source":{"kind":"arxiv","id":"2312.04403","version":1},"attestation_state":"computed","paper":{"title":"OT-Attack: Enhancing Adversarial Transferability of Vision-Language Models via Optimal Transport Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dongchen Han, Jindong Gu, Xiaochun Cao, Xiaojun Jia, Yang Bai, Yang Liu","submitted_at":"2023-12-07T16:16:50Z","abstract_excerpt":"Vision-language pre-training (VLP) models demonstrate impressive abilities in processing both images and text. However, they are vulnerable to multi-modal adversarial examples (AEs). Investigating the generation of high-transferability adversarial examples is crucial for uncovering VLP models' vulnerabilities in practical scenarios. Recent works have indicated that leveraging data augmentation and image-text modal interactions can enhance the transferability of adversarial examples for VLP models significantly. However, they do not consider the optimal alignment problem between dataaugmented i"},"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":"2312.04403","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-07T16:16:50Z","cross_cats_sorted":[],"title_canon_sha256":"c1a8b21bae47da432bc8523a038eaab41d2be72e556cb2977fee65c3cde130e1","abstract_canon_sha256":"d361495512e5b3d1549d7c59803f188dde74b8100dd25cecfec6f8a1805d237a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:21:33.882019Z","signature_b64":"YFnncbTOl1U14KPN0nUQrOpSlTWbH4r8zZ0R8L9OKScmBLWE0tYERoAdzZ59exRjPbul+xMvW1uyljeTreahBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e9f10f8c5d83f15d4e8c4f64630c9538949f9b27bf8384eff552d399f59b0703","last_reissued_at":"2026-07-05T07:21:33.881492Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:21:33.881492Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"OT-Attack: Enhancing Adversarial Transferability of Vision-Language Models via Optimal Transport Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dongchen Han, Jindong Gu, Xiaochun Cao, Xiaojun Jia, Yang Bai, Yang Liu","submitted_at":"2023-12-07T16:16:50Z","abstract_excerpt":"Vision-language pre-training (VLP) models demonstrate impressive abilities in processing both images and text. However, they are vulnerable to multi-modal adversarial examples (AEs). Investigating the generation of high-transferability adversarial examples is crucial for uncovering VLP models' vulnerabilities in practical scenarios. Recent works have indicated that leveraging data augmentation and image-text modal interactions can enhance the transferability of adversarial examples for VLP models significantly. However, they do not consider the optimal alignment problem between dataaugmented i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.04403","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/2312.04403/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":"2312.04403","created_at":"2026-07-05T07:21:33.881556+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.04403v1","created_at":"2026-07-05T07:21:33.881556+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.04403","created_at":"2026-07-05T07:21:33.881556+00:00"},{"alias_kind":"pith_short_12","alias_value":"5HYQ7DC5QPYV","created_at":"2026-07-05T07:21:33.881556+00:00"},{"alias_kind":"pith_short_16","alias_value":"5HYQ7DC5QPYV2TUM","created_at":"2026-07-05T07:21:33.881556+00:00"},{"alias_kind":"pith_short_8","alias_value":"5HYQ7DC5","created_at":"2026-07-05T07:21:33.881556+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.07706","citing_title":"MLingualFC: Evaluating Jailbreak Vulnerabilities in Multilingual Vision-Language Models","ref_index":105,"is_internal_anchor":false},{"citing_arxiv_id":"2502.05206","citing_title":"Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety","ref_index":232,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11716","citing_title":"SafeSteer: A Decoding-level Defense Mechanism for Multimodal Large Language Models","ref_index":14,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5HYQ7DC5QPYV2TUMJ5SGGDEVHC","json":"https://pith.science/pith/5HYQ7DC5QPYV2TUMJ5SGGDEVHC.json","graph_json":"https://pith.science/api/pith-number/5HYQ7DC5QPYV2TUMJ5SGGDEVHC/graph.json","events_json":"https://pith.science/api/pith-number/5HYQ7DC5QPYV2TUMJ5SGGDEVHC/events.json","paper":"https://pith.science/paper/5HYQ7DC5"},"agent_actions":{"view_html":"https://pith.science/pith/5HYQ7DC5QPYV2TUMJ5SGGDEVHC","download_json":"https://pith.science/pith/5HYQ7DC5QPYV2TUMJ5SGGDEVHC.json","view_paper":"https://pith.science/paper/5HYQ7DC5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.04403&json=true","fetch_graph":"https://pith.science/api/pith-number/5HYQ7DC5QPYV2TUMJ5SGGDEVHC/graph.json","fetch_events":"https://pith.science/api/pith-number/5HYQ7DC5QPYV2TUMJ5SGGDEVHC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5HYQ7DC5QPYV2TUMJ5SGGDEVHC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5HYQ7DC5QPYV2TUMJ5SGGDEVHC/action/storage_attestation","attest_author":"https://pith.science/pith/5HYQ7DC5QPYV2TUMJ5SGGDEVHC/action/author_attestation","sign_citation":"https://pith.science/pith/5HYQ7DC5QPYV2TUMJ5SGGDEVHC/action/citation_signature","submit_replication":"https://pith.science/pith/5HYQ7DC5QPYV2TUMJ5SGGDEVHC/action/replication_record"}},"created_at":"2026-07-05T07:21:33.881556+00:00","updated_at":"2026-07-05T07:21:33.881556+00:00"}