{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:QDSRAB57KZF23XOELSC4THVIKB","short_pith_number":"pith:QDSRAB57","schema_version":"1.0","canonical_sha256":"80e51007bf564badddc45c85c99ea8507966a0b3e3104184d9f50deee518b146","source":{"kind":"arxiv","id":"2503.13962","version":1},"attestation_state":"computed","paper":{"title":"Survey of Adversarial Robustness in Multimodal Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chengze Jiang, Jie Gui, Minjing Dong, Zhuangzhuang Wang","submitted_at":"2025-03-18T06:54:59Z","abstract_excerpt":"Multimodal Large Language Models (MLLMs) have demonstrated exceptional performance in artificial intelligence by facilitating integrated understanding across diverse modalities, including text, images, video, audio, and speech. However, their deployment in real-world applications raises significant concerns about adversarial vulnerabilities that could compromise their safety and reliability. Unlike unimodal models, MLLMs face unique challenges due to the interdependencies among modalities, making them susceptible to modality-specific threats and cross-modal adversarial manipulations. This pape"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2503.13962","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-18T06:54:59Z","cross_cats_sorted":[],"title_canon_sha256":"80f68415a73d9b23cca2c4188cdda6151109ace10b03117a323b733937cbc610","abstract_canon_sha256":"fd328537778521ee8ff4010bab45016f107444df3763fd2e67c05ea200caae20"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:33:22.561084Z","signature_b64":"heQIixxU2h6296TTPqQW1SaL/kYp2IgWevFa07/PBv2SpTuUrFcozL/5Iz+IGuxknOEVhTryeBWKKZWnaqckCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"80e51007bf564badddc45c85c99ea8507966a0b3e3104184d9f50deee518b146","last_reissued_at":"2026-07-05T10:33:22.560609Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:33:22.560609Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Survey of Adversarial Robustness in Multimodal Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chengze Jiang, Jie Gui, Minjing Dong, Zhuangzhuang Wang","submitted_at":"2025-03-18T06:54:59Z","abstract_excerpt":"Multimodal Large Language Models (MLLMs) have demonstrated exceptional performance in artificial intelligence by facilitating integrated understanding across diverse modalities, including text, images, video, audio, and speech. However, their deployment in real-world applications raises significant concerns about adversarial vulnerabilities that could compromise their safety and reliability. Unlike unimodal models, MLLMs face unique challenges due to the interdependencies among modalities, making them susceptible to modality-specific threats and cross-modal adversarial manipulations. This pape"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.13962","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2503.13962/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2503.13962","created_at":"2026-07-05T10:33:22.560667+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.13962v1","created_at":"2026-07-05T10:33:22.560667+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.13962","created_at":"2026-07-05T10:33:22.560667+00:00"},{"alias_kind":"pith_short_12","alias_value":"QDSRAB57KZF2","created_at":"2026-07-05T10:33:22.560667+00:00"},{"alias_kind":"pith_short_16","alias_value":"QDSRAB57KZF23XOE","created_at":"2026-07-05T10:33:22.560667+00:00"},{"alias_kind":"pith_short_8","alias_value":"QDSRAB57","created_at":"2026-07-05T10:33:22.560667+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2511.14159","citing_title":"MVI-Bench: A Comprehensive Benchmark for Evaluating Robustness to Misleading Visual Inputs in LVLMs","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2506.07180","citing_title":"Flattery in Motion: Benchmarking and Analyzing Sycophancy in Video-LLMs","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2509.22220","citing_title":"StableToken: A Noise-Robust Semantic Speech Tokenizer for Resilient SpeechLLMs","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2601.23179","citing_title":"Universal Adversarial Attacks against Closed-Source MLLMs via Target-View Routed Meta Optimization","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17243","citing_title":"RemoteShield: Enable Robust Multimodal Large Language Models for Earth Observation","ref_index":16,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QDSRAB57KZF23XOELSC4THVIKB","json":"https://pith.science/pith/QDSRAB57KZF23XOELSC4THVIKB.json","graph_json":"https://pith.science/api/pith-number/QDSRAB57KZF23XOELSC4THVIKB/graph.json","events_json":"https://pith.science/api/pith-number/QDSRAB57KZF23XOELSC4THVIKB/events.json","paper":"https://pith.science/paper/QDSRAB57"},"agent_actions":{"view_html":"https://pith.science/pith/QDSRAB57KZF23XOELSC4THVIKB","download_json":"https://pith.science/pith/QDSRAB57KZF23XOELSC4THVIKB.json","view_paper":"https://pith.science/paper/QDSRAB57","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.13962&json=true","fetch_graph":"https://pith.science/api/pith-number/QDSRAB57KZF23XOELSC4THVIKB/graph.json","fetch_events":"https://pith.science/api/pith-number/QDSRAB57KZF23XOELSC4THVIKB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QDSRAB57KZF23XOELSC4THVIKB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QDSRAB57KZF23XOELSC4THVIKB/action/storage_attestation","attest_author":"https://pith.science/pith/QDSRAB57KZF23XOELSC4THVIKB/action/author_attestation","sign_citation":"https://pith.science/pith/QDSRAB57KZF23XOELSC4THVIKB/action/citation_signature","submit_replication":"https://pith.science/pith/QDSRAB57KZF23XOELSC4THVIKB/action/replication_record"}},"created_at":"2026-07-05T10:33:22.560667+00:00","updated_at":"2026-07-05T10:33:22.560667+00:00"}