{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:YAPXKCDXOALA6YTUPCCALOFAJJ","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":"c01491c954d49e6563be281cc3133e60f3873a3ff0b77db9f6f2f196bc8a49dc","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-28T07:13:30Z","title_canon_sha256":"b9bd8dd5416268497ece9a95809ba451152e2283d139d4b7e128fa3b70161e20"},"schema_version":"1.0","source":{"id":"2405.17894","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.17894","created_at":"2026-07-05T09:19:57Z"},{"alias_kind":"arxiv_version","alias_value":"2405.17894v2","created_at":"2026-07-05T09:19:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.17894","created_at":"2026-07-05T09:19:57Z"},{"alias_kind":"pith_short_12","alias_value":"YAPXKCDXOALA","created_at":"2026-07-05T09:19:57Z"},{"alias_kind":"pith_short_16","alias_value":"YAPXKCDXOALA6YTU","created_at":"2026-07-05T09:19:57Z"},{"alias_kind":"pith_short_8","alias_value":"YAPXKCDX","created_at":"2026-07-05T09:19:57Z"}],"graph_snapshots":[{"event_id":"sha256:70d65ad37ca5bc1c4c830e57f7a06b7ff48fe9abad84f505307a8443d07c39c4","target":"graph","created_at":"2026-07-05T09:19:57Z","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/2405.17894/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advancements in Large Vision-Language Models (VLMs) have underscored their superiority in various multimodal tasks. However, the adversarial robustness of VLMs has not been fully explored. Existing methods mainly assess robustness through unimodal adversarial attacks that perturb images, while assuming inherent resilience against text-based attacks. Different from existing attacks, in this work we propose a more comprehensive strategy that jointly attacks both text and image modalities to exploit a broader spectrum of vulnerability within VLMs. Specifically, we propose a dual optimizati","authors_text":"Chuanjun Ji, Guangnan Ye, Hanxu Zhou, Ruofan Wang, Xingjun Ma, Yu-Gang Jiang","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-28T07:13:30Z","title":"White-box Multimodal Jailbreaks Against Large Vision-Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.17894","kind":"arxiv","version":2},"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:ed6137fc6c7be1177fc45cf31bd15d22a7d2d164b9196551a06a86e531395532","target":"record","created_at":"2026-07-05T09:19:57Z","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":"c01491c954d49e6563be281cc3133e60f3873a3ff0b77db9f6f2f196bc8a49dc","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-28T07:13:30Z","title_canon_sha256":"b9bd8dd5416268497ece9a95809ba451152e2283d139d4b7e128fa3b70161e20"},"schema_version":"1.0","source":{"id":"2405.17894","kind":"arxiv","version":2}},"canonical_sha256":"c01f75087770160f6274788405b8a04a7c488847adf8b53d48b414e13e0962a2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c01f75087770160f6274788405b8a04a7c488847adf8b53d48b414e13e0962a2","first_computed_at":"2026-07-05T09:19:57.843986Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:19:57.843986Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xcbuy4sUyL+FF7J3RuSVhBnwjkLOhkiNu/jSPQnC9jMj6L4iGAVV/JXl1ew36OiWmcQB5iV1s8pp5+csLM8gDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:19:57.844465Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.17894","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ed6137fc6c7be1177fc45cf31bd15d22a7d2d164b9196551a06a86e531395532","sha256:70d65ad37ca5bc1c4c830e57f7a06b7ff48fe9abad84f505307a8443d07c39c4"],"state_sha256":"82f9849c6969e9013241e60f6d3cc9275d6670d59c3639fcd1364f04a6233dbc"}