{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:TAMEUIHTSDGKTLJXNV6N64IZMP","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":"321b7b1b98173f19cf533aaf3a39c2108b314912fd4a7919b38ce9e6e474eec1","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-20T11:05:07Z","title_canon_sha256":"0ad5a15eff0bfd282404d72063fc0bbf17c290b341fe4b4ea2dc63a80b6a6313"},"schema_version":"1.0","source":{"id":"2403.13507","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.13507","created_at":"2026-07-05T07:58:50Z"},{"alias_kind":"arxiv_version","alias_value":"2403.13507v2","created_at":"2026-07-05T07:58:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.13507","created_at":"2026-07-05T07:58:50Z"},{"alias_kind":"pith_short_12","alias_value":"TAMEUIHTSDGK","created_at":"2026-07-05T07:58:50Z"},{"alias_kind":"pith_short_16","alias_value":"TAMEUIHTSDGKTLJX","created_at":"2026-07-05T07:58:50Z"},{"alias_kind":"pith_short_8","alias_value":"TAMEUIHT","created_at":"2026-07-05T07:58:50Z"}],"graph_snapshots":[{"event_id":"sha256:0b8e6fbeb34f9e89ecb0adcfeaac77da0b95768b8b30ba788523095c6886346f","target":"graph","created_at":"2026-07-05T07:58:50Z","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/2403.13507/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Despite the remarkable performance of video-based large language models (LLMs), their adversarial threat remains unexplored. To fill this gap, we propose the first adversarial attack tailored for video-based LLMs by crafting flow-based multi-modal adversarial perturbations on a small fraction of frames within a video, dubbed FMM-Attack. Extensive experiments show that our attack can effectively induce video-based LLMs to generate incorrect answers when videos are added with imperceptible adversarial perturbations. Intriguingly, our FMM-Attack can also induce garbling in the model output, promp","authors_text":"Jingyun Zhang, Jinmin Li, Kuofeng Gao, Shu-Tao Xia, Yang Bai, Yisen Wang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-20T11:05:07Z","title":"FMM-Attack: A Flow-based Multi-modal Adversarial Attack on Video-based LLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.13507","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":"sha256:066369299c21d64f2c3fba992dba312d71f08e00dbc3b323243b853ccc003b4b","target":"record","created_at":"2026-07-05T07:58:50Z","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":"321b7b1b98173f19cf533aaf3a39c2108b314912fd4a7919b38ce9e6e474eec1","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-20T11:05:07Z","title_canon_sha256":"0ad5a15eff0bfd282404d72063fc0bbf17c290b341fe4b4ea2dc63a80b6a6313"},"schema_version":"1.0","source":{"id":"2403.13507","kind":"arxiv","version":2}},"canonical_sha256":"98184a20f390cca9ad376d7cdf711963e03fd70d117bde45d430d579557606fd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"98184a20f390cca9ad376d7cdf711963e03fd70d117bde45d430d579557606fd","first_computed_at":"2026-07-05T07:58:50.033848Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:58:50.033848Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"b8xQlE9pV7VgHSZdePYH2DpSQd3iay/yqkVypLrrd9VH6ECWoon69VTUjBZ7RuHlXYm/g6BAQfwJWrPnZO2XCA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:58:50.034401Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.13507","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:066369299c21d64f2c3fba992dba312d71f08e00dbc3b323243b853ccc003b4b","sha256:0b8e6fbeb34f9e89ecb0adcfeaac77da0b95768b8b30ba788523095c6886346f"],"state_sha256":"8a4c7e70e75de42a20b264e24ad217eac02e509284f0a929a2464a182f3289e1"}