{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:OAJJWNJ4JDBQPSQYDMYAJNDGEE","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":"b9caa054b0b4c3e677a6f6a49e2110f4b1bfc25b2bdeca7f79c45d8966faf87b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-02-15T13:25:12Z","title_canon_sha256":"f9f91ca9aa6a5e89475e70444436c2d36ac8fb1eba3d0cd86dd7a16f7c1830f2"},"schema_version":"1.0","source":{"id":"2502.10794","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.10794","created_at":"2026-07-05T11:22:36Z"},{"alias_kind":"arxiv_version","alias_value":"2502.10794v2","created_at":"2026-07-05T11:22:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.10794","created_at":"2026-07-05T11:22:36Z"},{"alias_kind":"pith_short_12","alias_value":"OAJJWNJ4JDBQ","created_at":"2026-07-05T11:22:36Z"},{"alias_kind":"pith_short_16","alias_value":"OAJJWNJ4JDBQPSQY","created_at":"2026-07-05T11:22:36Z"},{"alias_kind":"pith_short_8","alias_value":"OAJJWNJ4","created_at":"2026-07-05T11:22:36Z"}],"graph_snapshots":[{"event_id":"sha256:44f1613df7c1fa53f3b6acd2bae6fb596bc177feb89dedb3184caf80daa15c79","target":"graph","created_at":"2026-07-05T11:22:36Z","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/2502.10794/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multimodal Large Language Models (MLLMs) bridge the gap between visual and textual data, enabling a range of advanced applications. However, complex internal interactions among visual elements and their alignment with text can introduce vulnerabilities, which may be exploited to bypass safety mechanisms. To address this, we analyze the relationship between image content and task and find that the complexity of subimages, rather than their content, is key. Building on this insight, we propose the Distraction Hypothesis, followed by a novel framework called Contrasting Subimage Distraction Jailb","authors_text":"Anli Yan, Changyu Dong, Erdun Gao, Jiluan Fan, Kanghua Mo, Tao Li, Xin Lin, Zuopeng Yang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-02-15T13:25:12Z","title":"Distraction is All You Need for Multimodal Large Language Model Jailbreaking"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.10794","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":"sha256:26896d92060bfc3e7c2559b37be2e48e81091d4cbac9db23f6df29f90562a3cd","target":"record","created_at":"2026-07-05T11:22:36Z","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":"b9caa054b0b4c3e677a6f6a49e2110f4b1bfc25b2bdeca7f79c45d8966faf87b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-02-15T13:25:12Z","title_canon_sha256":"f9f91ca9aa6a5e89475e70444436c2d36ac8fb1eba3d0cd86dd7a16f7c1830f2"},"schema_version":"1.0","source":{"id":"2502.10794","kind":"arxiv","version":2}},"canonical_sha256":"70129b353c48c307ca181b3004b4662137e6aa5b136a224fcee3ae5095fd1263","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"70129b353c48c307ca181b3004b4662137e6aa5b136a224fcee3ae5095fd1263","first_computed_at":"2026-07-05T11:22:36.769702Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:22:36.769702Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"berltFqBymx+/aGGaI+JK3l9pK7UT3xB77U0vvXUazHsy/Krqtdi3XhQi3ndwZPaS7wrMQQl7cbo5iztx+TOAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:22:36.770205Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.10794","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:26896d92060bfc3e7c2559b37be2e48e81091d4cbac9db23f6df29f90562a3cd","sha256:44f1613df7c1fa53f3b6acd2bae6fb596bc177feb89dedb3184caf80daa15c79"],"state_sha256":"8626c604dab1a7bb87041581404c7696d0bbcdcaddfd6067795c03784455916d"}