{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:PNKFBKY3RJIXDKJON3AWL7Z5D3","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":"2d4864eea5b36b19edd08002e85cb99b591ec446507ddda66f6e704b8e9c80d9","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-16T15:20:08Z","title_canon_sha256":"1e1ce9da319231513227250a1906c3007755f38dd1589e3d91f158ade5ad7548"},"schema_version":"1.0","source":{"id":"2410.12662","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.12662","created_at":"2026-07-05T10:21:24Z"},{"alias_kind":"arxiv_version","alias_value":"2410.12662v2","created_at":"2026-07-05T10:21:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.12662","created_at":"2026-07-05T10:21:24Z"},{"alias_kind":"pith_short_12","alias_value":"PNKFBKY3RJIX","created_at":"2026-07-05T10:21:24Z"},{"alias_kind":"pith_short_16","alias_value":"PNKFBKY3RJIXDKJO","created_at":"2026-07-05T10:21:24Z"},{"alias_kind":"pith_short_8","alias_value":"PNKFBKY3","created_at":"2026-07-05T10:21:24Z"}],"graph_snapshots":[{"event_id":"sha256:a9eb046bb3c3642361891b7713fdde1aa8a5a7b17fc872b092fe47fa08cb3713","target":"graph","created_at":"2026-07-05T10:21:24Z","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/2410.12662/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision-language alignment in Large Vision-Language Models (LVLMs) successfully enables LLMs to understand visual input. However, we find that existing vision-language alignment methods fail to transfer the existing safety mechanism for text in LLMs to vision, which leads to vulnerabilities in toxic image. To explore the cause of this problem, we give the insightful explanation of where and how the safety mechanism of LVLMs operates and conduct comparative analysis between text and vision. We find that the hidden states at the specific transformer layers play a crucial role in the successful ac","authors_text":"Huawei Shen, Liang Pang, Shicheng Xu, Xueqi Cheng, Yunchang Zhu","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-16T15:20:08Z","title":"Cross-Modal Safety Mechanism Transfer in Large Vision-Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.12662","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":"sha256:25e1616b50d6f8f67ead2f36ddf87707b010ced684f54cc188a1b5ed037dbaf1","target":"record","created_at":"2026-07-05T10:21:24Z","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":"2d4864eea5b36b19edd08002e85cb99b591ec446507ddda66f6e704b8e9c80d9","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-16T15:20:08Z","title_canon_sha256":"1e1ce9da319231513227250a1906c3007755f38dd1589e3d91f158ade5ad7548"},"schema_version":"1.0","source":{"id":"2410.12662","kind":"arxiv","version":2}},"canonical_sha256":"7b5450ab1b8a5171a92e6ec165ff3d1ef799ccea550adfffe94a3b2d4934887a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7b5450ab1b8a5171a92e6ec165ff3d1ef799ccea550adfffe94a3b2d4934887a","first_computed_at":"2026-07-05T10:21:24.839100Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:21:24.839100Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"T403AKnIziwC9RQzEtOhAKzfLTJqcuXi0mlod/QVPcai8IGs9+tyIZFtBESmRbBtzcGUeThv7xNmQbxeWWvUBw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:21:24.839630Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.12662","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:25e1616b50d6f8f67ead2f36ddf87707b010ced684f54cc188a1b5ed037dbaf1","sha256:a9eb046bb3c3642361891b7713fdde1aa8a5a7b17fc872b092fe47fa08cb3713"],"state_sha256":"267cae7738f50200c298b52327764cac2141af3693cf4c4567dff7e902050c18"}