{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:YWXWXN2TT4ENB35FFDINOKLDIF","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":"9fa90723260aeb66c44c7f833779120becb152f22070f21eec3f9a66cc27f689","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-09T09:06:56Z","title_canon_sha256":"38a4d7a324d3293e0391089814bd6b77df48ca576989660ac9d6068045f6d111"},"schema_version":"1.0","source":{"id":"2410.06699","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.06699","created_at":"2026-07-05T09:18:05Z"},{"alias_kind":"arxiv_version","alias_value":"2410.06699v1","created_at":"2026-07-05T09:18:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.06699","created_at":"2026-07-05T09:18:05Z"},{"alias_kind":"pith_short_12","alias_value":"YWXWXN2TT4EN","created_at":"2026-07-05T09:18:05Z"},{"alias_kind":"pith_short_16","alias_value":"YWXWXN2TT4ENB35F","created_at":"2026-07-05T09:18:05Z"},{"alias_kind":"pith_short_8","alias_value":"YWXWXN2T","created_at":"2026-07-05T09:18:05Z"}],"graph_snapshots":[{"event_id":"sha256:895b5b0d1254b4a64ecf728e051c1bc09053277a64c342833c440b18114cec20","target":"graph","created_at":"2026-07-05T09:18:05Z","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/2410.06699/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large vision-language models (LVLMs) integrate visual information into large language models, showcasing remarkable multi-modal conversational capabilities. However, the visual modules introduces new challenges in terms of robustness for LVLMs, as attackers can craft adversarial images that are visually clean but may mislead the model to generate incorrect answers. In general, LVLMs rely on vision encoders to transform images into visual tokens, which are crucial for the language models to perceive image contents effectively. Therefore, we are curious about one question: Can LVLMs still genera","authors_text":"Chaohu Liu, Deqiang Jiang, Haoyu Cao, Linli Xu, Yanqiu Qu, Yubo Wang","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-09T09:06:56Z","title":"Break the Visual Perception: Adversarial Attacks Targeting Encoded Visual Tokens of Large Vision-Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.06699","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:b9ea852605ee57a25cde4904d093b8a24403f12091c7c9eaafe1d3f8d5ab61ad","target":"record","created_at":"2026-07-05T09:18:05Z","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":"9fa90723260aeb66c44c7f833779120becb152f22070f21eec3f9a66cc27f689","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-09T09:06:56Z","title_canon_sha256":"38a4d7a324d3293e0391089814bd6b77df48ca576989660ac9d6068045f6d111"},"schema_version":"1.0","source":{"id":"2410.06699","kind":"arxiv","version":1}},"canonical_sha256":"c5af6bb7539f08d0efa528d0d72963415dc404319c410876723c89bc7b7ee7d2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c5af6bb7539f08d0efa528d0d72963415dc404319c410876723c89bc7b7ee7d2","first_computed_at":"2026-07-05T09:18:05.830133Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:18:05.830133Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"QMVpPJkyDZsoYFcplKSCoVOdQfUUL1J+1DgXMMOOsDUgAjiCGciODH7CIsr/ojDVoDDTjuW/7ouqLgJozaAJCA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:18:05.830613Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.06699","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b9ea852605ee57a25cde4904d093b8a24403f12091c7c9eaafe1d3f8d5ab61ad","sha256:895b5b0d1254b4a64ecf728e051c1bc09053277a64c342833c440b18114cec20"],"state_sha256":"1d638c776c47a4d8732ed91d3a50d128e8a4f51f46593b298a2b4a0730eb84ed"}