{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:R7DSUVG7I46SN3UDVMI3XW2HCQ","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":"deee94bb00921f4176d95d4c3054f63af108afdb24c523680e65dcebb226d488","cross_cats_sorted":["cs.CR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-06T13:00:42Z","title_canon_sha256":"c37f5e7d256542e9265e7e09f733c47fc149d9beb992fb1c8058cc7fc2a99d17"},"schema_version":"1.0","source":{"id":"2406.04031","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.04031","created_at":"2026-07-05T08:38:38Z"},{"alias_kind":"arxiv_version","alias_value":"2406.04031v2","created_at":"2026-07-05T08:38:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.04031","created_at":"2026-07-05T08:38:38Z"},{"alias_kind":"pith_short_12","alias_value":"R7DSUVG7I46S","created_at":"2026-07-05T08:38:38Z"},{"alias_kind":"pith_short_16","alias_value":"R7DSUVG7I46SN3UD","created_at":"2026-07-05T08:38:38Z"},{"alias_kind":"pith_short_8","alias_value":"R7DSUVG7","created_at":"2026-07-05T08:38:38Z"}],"graph_snapshots":[{"event_id":"sha256:8c81cc276ed8c4d00a835503cae0decfecf5a9daf1f52070b8dd8b092b0b1018","target":"graph","created_at":"2026-07-05T08:38:38Z","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/2406.04031/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In the realm of large vision language models (LVLMs), jailbreak attacks serve as a red-teaming approach to bypass guardrails and uncover safety implications. Existing jailbreaks predominantly focus on the visual modality, perturbing solely visual inputs in the prompt for attacks. However, they fall short when confronted with aligned models that fuse visual and textual features simultaneously for generation. To address this limitation, this paper introduces the Bi-Modal Adversarial Prompt Attack (BAP), which executes jailbreaks by optimizing textual and visual prompts cohesively. Initially, we ","authors_text":"Aishan Liu, Dacheng Tao, Siyuan Liang, Tianyuan Zhang, Xianglong Liu, Zhengmin Yu, Zonghao Ying","cross_cats":["cs.CR"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-06T13:00:42Z","title":"Jailbreak Vision Language Models via Bi-Modal Adversarial Prompt"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.04031","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:c6498546b4348666f9987bacd1716def778c4ab7c60317e0b0d9ce35ee4e3ba5","target":"record","created_at":"2026-07-05T08:38:38Z","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":"deee94bb00921f4176d95d4c3054f63af108afdb24c523680e65dcebb226d488","cross_cats_sorted":["cs.CR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-06T13:00:42Z","title_canon_sha256":"c37f5e7d256542e9265e7e09f733c47fc149d9beb992fb1c8058cc7fc2a99d17"},"schema_version":"1.0","source":{"id":"2406.04031","kind":"arxiv","version":2}},"canonical_sha256":"8fc72a54df473d26ee83ab11bbdb4714071db9d17273e090c17cc9d26e9485a3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8fc72a54df473d26ee83ab11bbdb4714071db9d17273e090c17cc9d26e9485a3","first_computed_at":"2026-07-05T08:38:38.456606Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:38:38.456606Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3lUzSg0twbALfYwyRnyYBqGkUm9FYEuq7sqzqXAMZ4v0+jD7XOfFch47NcvPk0URc0zgjEAnEZA2nWfz0vn7Bg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:38:38.457016Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.04031","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c6498546b4348666f9987bacd1716def778c4ab7c60317e0b0d9ce35ee4e3ba5","sha256:8c81cc276ed8c4d00a835503cae0decfecf5a9daf1f52070b8dd8b092b0b1018"],"state_sha256":"b33da3583529980d938b7396e26bc60cbb0ee997c0e8566b57e3d376adb9c001"}