{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:R26JHEFS7GHKYAP4BCUFOAGXRF","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":"4691ff36167969eef341f51d1bdd890b29603ce8189c16a86ed5c299c25446de","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-16T07:02:15Z","title_canon_sha256":"e55d63874b57604cab82373273249c10cbcb1afa27d73a77a47ff47b4b929d4a"},"schema_version":"1.0","source":{"id":"2507.11968","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.11968","created_at":"2026-07-05T11:38:12Z"},{"alias_kind":"arxiv_version","alias_value":"2507.11968v1","created_at":"2026-07-05T11:38:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.11968","created_at":"2026-07-05T11:38:12Z"},{"alias_kind":"pith_short_12","alias_value":"R26JHEFS7GHK","created_at":"2026-07-05T11:38:12Z"},{"alias_kind":"pith_short_16","alias_value":"R26JHEFS7GHKYAP4","created_at":"2026-07-05T11:38:12Z"},{"alias_kind":"pith_short_8","alias_value":"R26JHEFS","created_at":"2026-07-05T11:38:12Z"}],"graph_snapshots":[{"event_id":"sha256:c085a828e2270ea7ef583b1117d368c7ec72a8b27fb8493e72dfb67e1d12d614","target":"graph","created_at":"2026-07-05T11:38:12Z","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/2507.11968/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multimodal Large Language Models (MLLMs) are increasingly used for content moderation, yet their robustness in short-form video contexts remains underexplored. Current safety evaluations often rely on unimodal attacks, failing to address combined attack vulnerabilities. In this paper, we introduce a comprehensive framework for evaluating the tri-modal safety of MLLMs. First, we present the Short-Video Multimodal Adversarial (SVMA) dataset, comprising diverse short-form videos with human-guided synthetic adversarial attacks. Second, we propose ChimeraBreak, a novel tri-modal attack strategy tha","authors_text":"Mohammed Jawwadul Islam, Montasir Chowdhury, Sadia Ahmmed, Sahid Hossain Mustakim, S M Jishanul Islam, Swakkhar Shatabda, Syed Tasdid Azam Dhrubo, Tashfia Sikder, Ummay Maria Muna","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-16T07:02:15Z","title":"Watch, Listen, Understand, Mislead: Tri-modal Adversarial Attacks on Short Videos for Content Appropriateness Evaluation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.11968","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":"sha256:579ed55836dd7975300bc39ad59b5f5cac2c915f1e56a36eb3aab310ce868e0f","target":"record","created_at":"2026-07-05T11:38:12Z","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":"4691ff36167969eef341f51d1bdd890b29603ce8189c16a86ed5c299c25446de","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-16T07:02:15Z","title_canon_sha256":"e55d63874b57604cab82373273249c10cbcb1afa27d73a77a47ff47b4b929d4a"},"schema_version":"1.0","source":{"id":"2507.11968","kind":"arxiv","version":1}},"canonical_sha256":"8ebc9390b2f98eac01fc08a85700d78975fb4afd99a0327ec3e66067550312a1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8ebc9390b2f98eac01fc08a85700d78975fb4afd99a0327ec3e66067550312a1","first_computed_at":"2026-07-05T11:38:12.025171Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:38:12.025171Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"eeJEjNEJW3CrXZcRk+Mc5RJpvWmMuvCpn0T8q5RDYo1Mj9EhUCxsoAk+zBlKzuMQP+tsFX+y6JYACxyyCbAEAg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:38:12.025696Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.11968","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:579ed55836dd7975300bc39ad59b5f5cac2c915f1e56a36eb3aab310ce868e0f","sha256:c085a828e2270ea7ef583b1117d368c7ec72a8b27fb8493e72dfb67e1d12d614"],"state_sha256":"32ad643ffeab0a9688f46616349828c43083970dba3474b1af141ef58fb754fd"}