{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:4MTYIV3BSAACICTHCQVDNXGE7R","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":"414ae7cc2725930d0837497eeea0188e41ae67a81560d0dd25361c6bdec8c002","cross_cats_sorted":["cs.AI","cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2025-06-13T07:22:36Z","title_canon_sha256":"668dbf1f8450304fba777235fc9738317103fcb3b51c366c6b1074353541e005"},"schema_version":"1.0","source":{"id":"2506.11521","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.11521","created_at":"2026-07-05T11:21:06Z"},{"alias_kind":"arxiv_version","alias_value":"2506.11521v1","created_at":"2026-07-05T11:21:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.11521","created_at":"2026-07-05T11:21:06Z"},{"alias_kind":"pith_short_12","alias_value":"4MTYIV3BSAAC","created_at":"2026-07-05T11:21:06Z"},{"alias_kind":"pith_short_16","alias_value":"4MTYIV3BSAACICTH","created_at":"2026-07-05T11:21:06Z"},{"alias_kind":"pith_short_8","alias_value":"4MTYIV3B","created_at":"2026-07-05T11:21:06Z"}],"graph_snapshots":[{"event_id":"sha256:2d925a274af21fb8fa82996ae945a15abb1f4f8234324e49bfbb7a5c0b009318","target":"graph","created_at":"2026-07-05T11:21:06Z","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/2506.11521/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multimodal large language models (MLLMs), which bridge the gap between audio-visual and natural language processing, achieve state-of-the-art performance on several audio-visual tasks. Despite the superior performance of MLLMs, the scarcity of high-quality audio-visual training data and computational resources necessitates the utilization of third-party data and open-source MLLMs, a trend that is increasingly observed in contemporary research. This prosperity masks significant security risks. Empirical studies demonstrate that the latest MLLMs can be manipulated to produce malicious or harmful","authors_text":"Jinming Wen, Shuai Zhao, Xinyi Wu, Yanhao Jia, Yuwen Li","cross_cats":["cs.AI","cs.MM"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2025-06-13T07:22:36Z","title":"Investigating Vulnerabilities and Defenses Against Audio-Visual Attacks: A Comprehensive Survey Emphasizing Multimodal Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.11521","kind":"arxiv","version":1},"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:c21cd6ae9dbf579b36ee079c67a002cf251270a462bd1a7c8af7082e01a102c0","target":"record","created_at":"2026-07-05T11:21:06Z","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":"414ae7cc2725930d0837497eeea0188e41ae67a81560d0dd25361c6bdec8c002","cross_cats_sorted":["cs.AI","cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2025-06-13T07:22:36Z","title_canon_sha256":"668dbf1f8450304fba777235fc9738317103fcb3b51c366c6b1074353541e005"},"schema_version":"1.0","source":{"id":"2506.11521","kind":"arxiv","version":1}},"canonical_sha256":"e3278457619000240a67142a36dcc4fc63c3bc42a3bee2c3bb6f92edd3b0facb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e3278457619000240a67142a36dcc4fc63c3bc42a3bee2c3bb6f92edd3b0facb","first_computed_at":"2026-07-05T11:21:06.024180Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:21:06.024180Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6oaU9NEIr6m4B+MJpWiMwF5H9iI5Qmw5wDPAS44tw0kleJxCmXE6OOA81ATQHheH5qS/73yYfGgj8zvU/fu7Bg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:21:06.024839Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.11521","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c21cd6ae9dbf579b36ee079c67a002cf251270a462bd1a7c8af7082e01a102c0","sha256:2d925a274af21fb8fa82996ae945a15abb1f4f8234324e49bfbb7a5c0b009318"],"state_sha256":"aa8d6b46f027b3787dd116fadcfb949becb95a536792952e2b88060d175ebe99"}