{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:KHNQY7PCQBOH7OZSAXUVOWFNAE","short_pith_number":"pith:KHNQY7PC","schema_version":"1.0","canonical_sha256":"51db0c7de2805c7fbb3205e95758ad0120d7d996de447e89be4298c4d3a66dfd","source":{"kind":"arxiv","id":"2501.13563","version":1},"attestation_state":"computed","paper":{"title":"Black-Box Adversarial Attack on Vision Language Models for Autonomous Driving","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Aishan Liu, Dacheng Tao, Lu Wang, Siyuan Liang, Tianyuan Zhang, Xianglong Liu, Yang Qu, Yuwei Chen","submitted_at":"2025-01-23T11:10:02Z","abstract_excerpt":"Vision-language models (VLMs) have significantly advanced autonomous driving (AD) by enhancing reasoning capabilities; however, these models remain highly susceptible to adversarial attacks. While existing research has explored white-box attacks to some extent, the more practical and challenging black-box scenarios remain largely underexplored due to their inherent difficulty. In this paper, we take the first step toward designing black-box adversarial attacks specifically targeting VLMs in AD. We identify two key challenges for achieving effective black-box attacks in this context: the effect"},"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":"2501.13563","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-01-23T11:10:02Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a90678f9c6b8e8ed4c8f5d19d2017074a62f2ebe811dc27126b6b36920848db7","abstract_canon_sha256":"19f3891c0a6885bc959e4aa6ced2673fdeafb59b010adecee5d1bfbfa7b8f5c5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:04:30.456286Z","signature_b64":"YFCbNCD58ctOwY5I1TMeF2a4Upzk8birnLamp2Mn9bhzjiH1G7ENB7KXCXE4fi9j/pToqzMJVCdl3wMs7JUeBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"51db0c7de2805c7fbb3205e95758ad0120d7d996de447e89be4298c4d3a66dfd","last_reissued_at":"2026-07-05T10:04:30.455802Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:04:30.455802Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Black-Box Adversarial Attack on Vision Language Models for Autonomous Driving","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Aishan Liu, Dacheng Tao, Lu Wang, Siyuan Liang, Tianyuan Zhang, Xianglong Liu, Yang Qu, Yuwei Chen","submitted_at":"2025-01-23T11:10:02Z","abstract_excerpt":"Vision-language models (VLMs) have significantly advanced autonomous driving (AD) by enhancing reasoning capabilities; however, these models remain highly susceptible to adversarial attacks. While existing research has explored white-box attacks to some extent, the more practical and challenging black-box scenarios remain largely underexplored due to their inherent difficulty. In this paper, we take the first step toward designing black-box adversarial attacks specifically targeting VLMs in AD. We identify two key challenges for achieving effective black-box attacks in this context: the effect"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.13563","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/2501.13563/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":"2501.13563","created_at":"2026-07-05T10:04:30.455863+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.13563v1","created_at":"2026-07-05T10:04:30.455863+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.13563","created_at":"2026-07-05T10:04:30.455863+00:00"},{"alias_kind":"pith_short_12","alias_value":"KHNQY7PCQBOH","created_at":"2026-07-05T10:04:30.455863+00:00"},{"alias_kind":"pith_short_16","alias_value":"KHNQY7PCQBOH7OZS","created_at":"2026-07-05T10:04:30.455863+00:00"},{"alias_kind":"pith_short_8","alias_value":"KHNQY7PC","created_at":"2026-07-05T10:04:30.455863+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":8,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.05783","citing_title":"Benchmarking the Robustness of Autonomous Driving to Environmental Illusions: A Lane Perception Perspective","ref_index":131,"is_internal_anchor":true},{"citing_arxiv_id":"2605.29114","citing_title":"ReasonBreak: Probing Vulnerabilities in Reasoning-Enabled Vision-Language-Action Models for Autonomous Driving","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2605.23220","citing_title":"WMAttack: Automated Attack Search for Adversarial Evaluation of World-Model Agents","ref_index":47,"is_internal_anchor":false},{"citing_arxiv_id":"2512.21815","citing_title":"High-Entropy Tokens as Multimodal Failure Points in Vision-Language Models","ref_index":43,"is_internal_anchor":false},{"citing_arxiv_id":"2602.16144","citing_title":"Missing-by-Design: Certifiable Modality Deletion for Revocable Multimodal Sentiment Analysis","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10386","citing_title":"GuardAD: Safeguarding Autonomous Driving MLLMs via Markovian Safety Logic","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00880","citing_title":"Adversarial Flow Matching for Imperceptible Attacks on End-to-End Autonomous Driving","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2604.04488","citing_title":"A Patch-based Cross-view Regularized Framework for Backdoor Defense in Multimodal Large Language Models","ref_index":40,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KHNQY7PCQBOH7OZSAXUVOWFNAE","json":"https://pith.science/pith/KHNQY7PCQBOH7OZSAXUVOWFNAE.json","graph_json":"https://pith.science/api/pith-number/KHNQY7PCQBOH7OZSAXUVOWFNAE/graph.json","events_json":"https://pith.science/api/pith-number/KHNQY7PCQBOH7OZSAXUVOWFNAE/events.json","paper":"https://pith.science/paper/KHNQY7PC"},"agent_actions":{"view_html":"https://pith.science/pith/KHNQY7PCQBOH7OZSAXUVOWFNAE","download_json":"https://pith.science/pith/KHNQY7PCQBOH7OZSAXUVOWFNAE.json","view_paper":"https://pith.science/paper/KHNQY7PC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.13563&json=true","fetch_graph":"https://pith.science/api/pith-number/KHNQY7PCQBOH7OZSAXUVOWFNAE/graph.json","fetch_events":"https://pith.science/api/pith-number/KHNQY7PCQBOH7OZSAXUVOWFNAE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KHNQY7PCQBOH7OZSAXUVOWFNAE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KHNQY7PCQBOH7OZSAXUVOWFNAE/action/storage_attestation","attest_author":"https://pith.science/pith/KHNQY7PCQBOH7OZSAXUVOWFNAE/action/author_attestation","sign_citation":"https://pith.science/pith/KHNQY7PCQBOH7OZSAXUVOWFNAE/action/citation_signature","submit_replication":"https://pith.science/pith/KHNQY7PCQBOH7OZSAXUVOWFNAE/action/replication_record"}},"created_at":"2026-07-05T10:04:30.455863+00:00","updated_at":"2026-07-05T10:04:30.455863+00:00"}