{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:KMZEALZXQY2VPHX6CZOIHQK4II","short_pith_number":"pith:KMZEALZX","schema_version":"1.0","canonical_sha256":"5332402f378635579efe165c83c15c4202e546c966004fc68e1db947566c74a0","source":{"kind":"arxiv","id":"2402.11083","version":1},"attestation_state":"computed","paper":{"title":"VQAttack: Transferable Adversarial Attacks on Visual Question Answering via Pre-trained Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fenglong Ma, Han Liu, Jiaqi Wang, Jinghui Chen, Muchao Ye, Tianrong Zhang, Ting Wang, Ziyi Yin","submitted_at":"2024-02-16T21:17:42Z","abstract_excerpt":"Visual Question Answering (VQA) is a fundamental task in computer vision and natural language process fields. Although the ``pre-training & finetuning'' learning paradigm significantly improves the VQA performance, the adversarial robustness of such a learning paradigm has not been explored. In this paper, we delve into a new problem: using a pre-trained multimodal source model to create adversarial image-text pairs and then transferring them to attack the target VQA models. Correspondingly, we propose a novel VQAttack model, which can iteratively generate both image and text perturbations wit"},"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":"2402.11083","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-02-16T21:17:42Z","cross_cats_sorted":[],"title_canon_sha256":"2863e53839859ba82cb0146a3f577262b9d77c79a34e3ab9c558b3fd3bb9db14","abstract_canon_sha256":"bc3fcea9671c9eb8fc2a89a5df31eb0fc3cce1a115677fd861f2ad197210b41e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:46:33.917597Z","signature_b64":"I2L9wW68IpHPsJCNZ0xdI6r7d72ZePRejwSMl/5ZsuFuyVNPH0ExHrmbFGT+6Nd+bfnkGEbKlZoHDRLg96a4Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5332402f378635579efe165c83c15c4202e546c966004fc68e1db947566c74a0","last_reissued_at":"2026-07-05T07:46:33.917025Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:46:33.917025Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VQAttack: Transferable Adversarial Attacks on Visual Question Answering via Pre-trained Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fenglong Ma, Han Liu, Jiaqi Wang, Jinghui Chen, Muchao Ye, Tianrong Zhang, Ting Wang, Ziyi Yin","submitted_at":"2024-02-16T21:17:42Z","abstract_excerpt":"Visual Question Answering (VQA) is a fundamental task in computer vision and natural language process fields. Although the ``pre-training & finetuning'' learning paradigm significantly improves the VQA performance, the adversarial robustness of such a learning paradigm has not been explored. In this paper, we delve into a new problem: using a pre-trained multimodal source model to create adversarial image-text pairs and then transferring them to attack the target VQA models. Correspondingly, we propose a novel VQAttack model, which can iteratively generate both image and text perturbations wit"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.11083","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/2402.11083/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":"2402.11083","created_at":"2026-07-05T07:46:33.917103+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.11083v1","created_at":"2026-07-05T07:46:33.917103+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.11083","created_at":"2026-07-05T07:46:33.917103+00:00"},{"alias_kind":"pith_short_12","alias_value":"KMZEALZXQY2V","created_at":"2026-07-05T07:46:33.917103+00:00"},{"alias_kind":"pith_short_16","alias_value":"KMZEALZXQY2VPHX6","created_at":"2026-07-05T07:46:33.917103+00:00"},{"alias_kind":"pith_short_8","alias_value":"KMZEALZX","created_at":"2026-07-05T07:46:33.917103+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.18706","citing_title":"SurvAttack: Black-Box Attack On Survival Models through Ontology-Informed EHR Perturbation","ref_index":47,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KMZEALZXQY2VPHX6CZOIHQK4II","json":"https://pith.science/pith/KMZEALZXQY2VPHX6CZOIHQK4II.json","graph_json":"https://pith.science/api/pith-number/KMZEALZXQY2VPHX6CZOIHQK4II/graph.json","events_json":"https://pith.science/api/pith-number/KMZEALZXQY2VPHX6CZOIHQK4II/events.json","paper":"https://pith.science/paper/KMZEALZX"},"agent_actions":{"view_html":"https://pith.science/pith/KMZEALZXQY2VPHX6CZOIHQK4II","download_json":"https://pith.science/pith/KMZEALZXQY2VPHX6CZOIHQK4II.json","view_paper":"https://pith.science/paper/KMZEALZX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.11083&json=true","fetch_graph":"https://pith.science/api/pith-number/KMZEALZXQY2VPHX6CZOIHQK4II/graph.json","fetch_events":"https://pith.science/api/pith-number/KMZEALZXQY2VPHX6CZOIHQK4II/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KMZEALZXQY2VPHX6CZOIHQK4II/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KMZEALZXQY2VPHX6CZOIHQK4II/action/storage_attestation","attest_author":"https://pith.science/pith/KMZEALZXQY2VPHX6CZOIHQK4II/action/author_attestation","sign_citation":"https://pith.science/pith/KMZEALZXQY2VPHX6CZOIHQK4II/action/citation_signature","submit_replication":"https://pith.science/pith/KMZEALZXQY2VPHX6CZOIHQK4II/action/replication_record"}},"created_at":"2026-07-05T07:46:33.917103+00:00","updated_at":"2026-07-05T07:46:33.917103+00:00"}