{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:P4W2HKKQ7WZGJV7QJNYLENKKRK","short_pith_number":"pith:P4W2HKKQ","schema_version":"1.0","canonical_sha256":"7f2da3a950fdb264d7f04b70b2354a8a907928ecff101be0127b4704bb1ce1ab","source":{"kind":"arxiv","id":"2408.08989","version":1},"attestation_state":"computed","paper":{"title":"Ask, Attend, Attack: A Effective Decision-Based Black-Box Targeted Attack for Image-to-Text Models","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.AI","authors_text":"Min Jiang, Qingyuan Zeng, Yiu-ming Cheung, Zhenzhong Wang","submitted_at":"2024-08-16T19:35:06Z","abstract_excerpt":"While image-to-text models have demonstrated significant advancements in various vision-language tasks, they remain susceptible to adversarial attacks. Existing white-box attacks on image-to-text models require access to the architecture, gradients, and parameters of the target model, resulting in low practicality. Although the recently proposed gray-box attacks have improved practicality, they suffer from semantic loss during the training process, which limits their targeted attack performance. To advance adversarial attacks of image-to-text models, this paper focuses on a challenging scenari"},"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":"2408.08989","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2024-08-16T19:35:06Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"fdd1a4f3b8fdf663d8c21e2bbb3c800367287e9d5aaa6159c1316c6a022db59e","abstract_canon_sha256":"f069304e01e650eb2471e08635d61f9e508787a231b924bf9fd111a7b0226525"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:56:26.472266Z","signature_b64":"iDzySB/sHXhABszKfmfEWWL0gNOe4dQ9nsYLq+kRtSfQqe0x8R6LkZ3eS/BAUr3+OhsyUxb2CtS6cdjDAoPjBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7f2da3a950fdb264d7f04b70b2354a8a907928ecff101be0127b4704bb1ce1ab","last_reissued_at":"2026-07-05T08:56:26.471827Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:56:26.471827Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Ask, Attend, Attack: A Effective Decision-Based Black-Box Targeted Attack for Image-to-Text Models","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.AI","authors_text":"Min Jiang, Qingyuan Zeng, Yiu-ming Cheung, Zhenzhong Wang","submitted_at":"2024-08-16T19:35:06Z","abstract_excerpt":"While image-to-text models have demonstrated significant advancements in various vision-language tasks, they remain susceptible to adversarial attacks. Existing white-box attacks on image-to-text models require access to the architecture, gradients, and parameters of the target model, resulting in low practicality. Although the recently proposed gray-box attacks have improved practicality, they suffer from semantic loss during the training process, which limits their targeted attack performance. To advance adversarial attacks of image-to-text models, this paper focuses on a challenging scenari"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.08989","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/2408.08989/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":"2408.08989","created_at":"2026-07-05T08:56:26.471880+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.08989v1","created_at":"2026-07-05T08:56:26.471880+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.08989","created_at":"2026-07-05T08:56:26.471880+00:00"},{"alias_kind":"pith_short_12","alias_value":"P4W2HKKQ7WZG","created_at":"2026-07-05T08:56:26.471880+00:00"},{"alias_kind":"pith_short_16","alias_value":"P4W2HKKQ7WZGJV7Q","created_at":"2026-07-05T08:56:26.471880+00:00"},{"alias_kind":"pith_short_8","alias_value":"P4W2HKKQ","created_at":"2026-07-05T08:56:26.471880+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.00055","citing_title":"LLM-Virus: Evolutionary Jailbreak Attack on Large Language Models","ref_index":17,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/P4W2HKKQ7WZGJV7QJNYLENKKRK","json":"https://pith.science/pith/P4W2HKKQ7WZGJV7QJNYLENKKRK.json","graph_json":"https://pith.science/api/pith-number/P4W2HKKQ7WZGJV7QJNYLENKKRK/graph.json","events_json":"https://pith.science/api/pith-number/P4W2HKKQ7WZGJV7QJNYLENKKRK/events.json","paper":"https://pith.science/paper/P4W2HKKQ"},"agent_actions":{"view_html":"https://pith.science/pith/P4W2HKKQ7WZGJV7QJNYLENKKRK","download_json":"https://pith.science/pith/P4W2HKKQ7WZGJV7QJNYLENKKRK.json","view_paper":"https://pith.science/paper/P4W2HKKQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.08989&json=true","fetch_graph":"https://pith.science/api/pith-number/P4W2HKKQ7WZGJV7QJNYLENKKRK/graph.json","fetch_events":"https://pith.science/api/pith-number/P4W2HKKQ7WZGJV7QJNYLENKKRK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/P4W2HKKQ7WZGJV7QJNYLENKKRK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/P4W2HKKQ7WZGJV7QJNYLENKKRK/action/storage_attestation","attest_author":"https://pith.science/pith/P4W2HKKQ7WZGJV7QJNYLENKKRK/action/author_attestation","sign_citation":"https://pith.science/pith/P4W2HKKQ7WZGJV7QJNYLENKKRK/action/citation_signature","submit_replication":"https://pith.science/pith/P4W2HKKQ7WZGJV7QJNYLENKKRK/action/replication_record"}},"created_at":"2026-07-05T08:56:26.471880+00:00","updated_at":"2026-07-05T08:56:26.471880+00:00"}