{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:BDOGV5CB3URXX4RP2AWLEJ7TIH","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":"7863cb665a79370cfaf74f9f27662408fbcd9c1063da7587ea66302214fc8c47","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2024-08-17T04:43:26Z","title_canon_sha256":"650da74a1335e2816e0cc4bf4a2e33328f0d040d517d26fb19c63e3c127e90cf"},"schema_version":"1.0","source":{"id":"2408.09093","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.09093","created_at":"2026-07-05T10:52:13Z"},{"alias_kind":"arxiv_version","alias_value":"2408.09093v3","created_at":"2026-07-05T10:52:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.09093","created_at":"2026-07-05T10:52:13Z"},{"alias_kind":"pith_short_12","alias_value":"BDOGV5CB3URX","created_at":"2026-07-05T10:52:13Z"},{"alias_kind":"pith_short_16","alias_value":"BDOGV5CB3URXX4RP","created_at":"2026-07-05T10:52:13Z"},{"alias_kind":"pith_short_8","alias_value":"BDOGV5CB","created_at":"2026-07-05T10:52:13Z"}],"graph_snapshots":[{"event_id":"sha256:b68e78da3d64bcdf139e822450c9bb9d05e9a74c0d755a858729a554e3a56f9e","target":"graph","created_at":"2026-07-05T10:52:13Z","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/2408.09093/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multimodal Large Language Models (MLLMs) have showcased impressive performance in a variety of multimodal tasks. On the other hand, the integration of additional image modality may allow the malicious users to inject harmful content inside the images for jailbreaking. Unlike text-based LLMs, where adversaries need to select discrete tokens to conceal their malicious intent using specific algorithms, the continuous nature of image signals provides a direct opportunity for adversaries to inject harmful intentions. In this work, we propose $\\textbf{BaThe}$ ($\\textbf{Ba}$ckdoor $\\textbf{T}$rigger ","authors_text":"Bryan Hooi, Haoran Li, Yangqiu Song, Yirui Zhang, Yulin Chen, Zihao Zheng","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2024-08-17T04:43:26Z","title":"BaThe: Defense against the Jailbreak Attack in Multimodal Large Language Models by Treating Harmful Instruction as Backdoor Trigger"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.09093","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":"sha256:486ca1829090bad651eeb06103936b0a650aee86985d95e47536c7bfd9643966","target":"record","created_at":"2026-07-05T10:52:13Z","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":"7863cb665a79370cfaf74f9f27662408fbcd9c1063da7587ea66302214fc8c47","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2024-08-17T04:43:26Z","title_canon_sha256":"650da74a1335e2816e0cc4bf4a2e33328f0d040d517d26fb19c63e3c127e90cf"},"schema_version":"1.0","source":{"id":"2408.09093","kind":"arxiv","version":3}},"canonical_sha256":"08dc6af441dd237bf22fd02cb227f341c59d0094018d548ac729adee0cabe546","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"08dc6af441dd237bf22fd02cb227f341c59d0094018d548ac729adee0cabe546","first_computed_at":"2026-07-05T10:52:13.489761Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:52:13.489761Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8JB+wmh5o76FyzsptjuCtXVzyCliUan3RayPYmDj21eqC02WQcLd9J1S55rJc344SfamPNCRG3NIqrZKgbspCg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:52:13.490254Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.09093","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:486ca1829090bad651eeb06103936b0a650aee86985d95e47536c7bfd9643966","sha256:b68e78da3d64bcdf139e822450c9bb9d05e9a74c0d755a858729a554e3a56f9e"],"state_sha256":"10539328559b12f0320ed2c4eb0103d05602cbe32f95c5fd46322bfcefa241dc"}