{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:UVML22ZSW5TWTDVG3LZYJFMWJL","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":"81238e52982560ea472a7ac03c01e58befa185bb80c446acc6b4054bd84716f8","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-02T14:34:48Z","title_canon_sha256":"40ca34cf46402c306101aefff7e6d1bc44b2b3fe4e51d87fafe90b8681aaa073"},"schema_version":"1.0","source":{"id":"2606.03713","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.03713","created_at":"2026-06-03T01:06:05Z"},{"alias_kind":"arxiv_version","alias_value":"2606.03713v1","created_at":"2026-06-03T01:06:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.03713","created_at":"2026-06-03T01:06:05Z"},{"alias_kind":"pith_short_12","alias_value":"UVML22ZSW5TW","created_at":"2026-06-03T01:06:05Z"},{"alias_kind":"pith_short_16","alias_value":"UVML22ZSW5TWTDVG","created_at":"2026-06-03T01:06:05Z"},{"alias_kind":"pith_short_8","alias_value":"UVML22ZS","created_at":"2026-06-03T01:06:05Z"}],"graph_snapshots":[{"event_id":"sha256:ede567db759d6b814ec569395accb0c8c5173f21ffe273ff62045795552fefae","target":"graph","created_at":"2026-06-03T01:06:05Z","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/2606.03713/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multi-modal Large Language Models (MLLMs) achieve strong performance on vision-language tasks, but incorporating visual inputs through a vision encoder (e.g., CLIP) substantially expands the attack surface, making these models vulnerable to visual adversarial perturbations. Prior defenses typically preserve compatibility with pretrained MLLMs by enforcing strict alignment to CLIP's original embedding space during adversarial fine-tuning; while practical, this constraint fundamentally limits achievable robustness. We present a systematic investigation of adversarial robustness in MLLMs. We firs","authors_text":"Hashmat Shadab Malik, Muzammal Naseer, Salman Khan","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-02T14:34:48Z","title":"Investigating Adversarial Robustness of Multi-modal Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.03713","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":"sha256:62834dfae9795cabc9be6d8228182e7badbcd94ff10b5519afc313c76f501c70","target":"record","created_at":"2026-06-03T01:06:05Z","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":"81238e52982560ea472a7ac03c01e58befa185bb80c446acc6b4054bd84716f8","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-02T14:34:48Z","title_canon_sha256":"40ca34cf46402c306101aefff7e6d1bc44b2b3fe4e51d87fafe90b8681aaa073"},"schema_version":"1.0","source":{"id":"2606.03713","kind":"arxiv","version":1}},"canonical_sha256":"a558bd6b32b767698ea6daf38495964add1fce336b6ea4c66861de72efec097e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a558bd6b32b767698ea6daf38495964add1fce336b6ea4c66861de72efec097e","first_computed_at":"2026-06-03T01:06:05.251484Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-03T01:06:05.251484Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"OS4JGaZv7p2Oh8tVimHol7Kc7T2GpN0fEu/U6tFjrumtBPfIgzT98vrysZXnhTdnyCINnOmXfPiGel2N+zVLAg==","signature_status":"signed_v1","signed_at":"2026-06-03T01:06:05.252052Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.03713","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:62834dfae9795cabc9be6d8228182e7badbcd94ff10b5519afc313c76f501c70","sha256:ede567db759d6b814ec569395accb0c8c5173f21ffe273ff62045795552fefae"],"state_sha256":"399e17126b7ac818a0e9936906a583a568811518387173e177eb83079f406438"}