{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:CN5LGE5HDTNNVHPEAUKON6UZPR","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"858ce15059f9cd679ee8ad9e4216b58ebcbd2dbb3a3c744d7a0377e77f950c28","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-19T05:10:10Z","title_canon_sha256":"edfe97c73fed8d45f0e5960c91e1e0249d2601aa733f59d9937a3498656a8599"},"schema_version":"1.0","source":{"id":"2403.12445","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.12445","created_at":"2026-07-05T08:43:27Z"},{"alias_kind":"arxiv_version","alias_value":"2403.12445v3","created_at":"2026-07-05T08:43:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.12445","created_at":"2026-07-05T08:43:27Z"},{"alias_kind":"pith_short_12","alias_value":"CN5LGE5HDTNN","created_at":"2026-07-05T08:43:27Z"},{"alias_kind":"pith_short_16","alias_value":"CN5LGE5HDTNNVHPE","created_at":"2026-07-05T08:43:27Z"},{"alias_kind":"pith_short_8","alias_value":"CN5LGE5H","created_at":"2026-07-05T08:43:27Z"}],"graph_snapshots":[{"event_id":"sha256:b3f930fc208737479a501d7115d84d782d5cfa88337efb307bdcfc26d1ed4873","target":"graph","created_at":"2026-07-05T08:43:27Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2403.12445/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision-language pre-training (VLP) models exhibit remarkable capabilities in comprehending both images and text, yet they remain susceptible to multimodal adversarial examples (AEs). Strengthening attacks and uncovering vulnerabilities, especially common issues in VLP models (e.g., high transferable AEs), can advance reliable and practical VLP models. A recent work (i.e., Set-level guidance attack) indicates that augmenting image-text pairs to increase AE diversity along the optimization path enhances the transferability of adversarial examples significantly. However, this approach predominant","authors_text":"Ivor Tsang, Qing Guo, Sensen Gao, Xiaojun Jia, Xuhong Ren","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-19T05:10:10Z","title":"Boosting Transferability in Vision-Language Attacks via Diversification along the Intersection Region of Adversarial Trajectory"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.12445","kind":"arxiv","version":3},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:1db2b83598c0f9ed27c262943dafb0eb48f0679e17dccdabe3139030c3fd70f9","target":"record","created_at":"2026-07-05T08:43:27Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"858ce15059f9cd679ee8ad9e4216b58ebcbd2dbb3a3c744d7a0377e77f950c28","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-19T05:10:10Z","title_canon_sha256":"edfe97c73fed8d45f0e5960c91e1e0249d2601aa733f59d9937a3498656a8599"},"schema_version":"1.0","source":{"id":"2403.12445","kind":"arxiv","version":3}},"canonical_sha256":"137ab313a71cdada9de40514e6fa997c41a3ee408966b72bbdeb2cfdd0df1e08","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"137ab313a71cdada9de40514e6fa997c41a3ee408966b72bbdeb2cfdd0df1e08","first_computed_at":"2026-07-05T08:43:27.233085Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:43:27.233085Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9Z4pn4mp37zhjRsJkMpG5Ixua0TOkYC9t7hMzFV5ogD/8vKUxEvcGMDZ6Bp/oG2dBa5EWvc5+Bf5FjOLp4REAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:43:27.233495Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.12445","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1db2b83598c0f9ed27c262943dafb0eb48f0679e17dccdabe3139030c3fd70f9","sha256:b3f930fc208737479a501d7115d84d782d5cfa88337efb307bdcfc26d1ed4873"],"state_sha256":"4faa5eb9f03fe8b024c228160701b28fb6854ffd52b035c7300d1c8bb503ea0c"}