{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:P4W2HKKQ7WZGJV7QJNYLENKKRK","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":"f069304e01e650eb2471e08635d61f9e508787a231b924bf9fd111a7b0226525","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2024-08-16T19:35:06Z","title_canon_sha256":"fdd1a4f3b8fdf663d8c21e2bbb3c800367287e9d5aaa6159c1316c6a022db59e"},"schema_version":"1.0","source":{"id":"2408.08989","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.08989","created_at":"2026-07-05T08:56:26Z"},{"alias_kind":"arxiv_version","alias_value":"2408.08989v1","created_at":"2026-07-05T08:56:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.08989","created_at":"2026-07-05T08:56:26Z"},{"alias_kind":"pith_short_12","alias_value":"P4W2HKKQ7WZG","created_at":"2026-07-05T08:56:26Z"},{"alias_kind":"pith_short_16","alias_value":"P4W2HKKQ7WZGJV7Q","created_at":"2026-07-05T08:56:26Z"},{"alias_kind":"pith_short_8","alias_value":"P4W2HKKQ","created_at":"2026-07-05T08:56:26Z"}],"graph_snapshots":[{"event_id":"sha256:0a0f2a1e5f20ceb6c8b7696268150088f5be955365be12d4171360c097da4e54","target":"graph","created_at":"2026-07-05T08:56:26Z","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/2408.08989/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Min Jiang, Qingyuan Zeng, Yiu-ming Cheung, Zhenzhong Wang","cross_cats":["cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2024-08-16T19:35:06Z","title":"Ask, Attend, Attack: A Effective Decision-Based Black-Box Targeted Attack for Image-to-Text Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.08989","kind":"arxiv","version":1},"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":"sha256:62f8a80e5978adac0c4cea61400c2972a0d8cdc9667eae7751655d79bd511373","target":"record","created_at":"2026-07-05T08:56:26Z","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":"f069304e01e650eb2471e08635d61f9e508787a231b924bf9fd111a7b0226525","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2024-08-16T19:35:06Z","title_canon_sha256":"fdd1a4f3b8fdf663d8c21e2bbb3c800367287e9d5aaa6159c1316c6a022db59e"},"schema_version":"1.0","source":{"id":"2408.08989","kind":"arxiv","version":1}},"canonical_sha256":"7f2da3a950fdb264d7f04b70b2354a8a907928ecff101be0127b4704bb1ce1ab","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7f2da3a950fdb264d7f04b70b2354a8a907928ecff101be0127b4704bb1ce1ab","first_computed_at":"2026-07-05T08:56:26.471827Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:56:26.471827Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"iDzySB/sHXhABszKfmfEWWL0gNOe4dQ9nsYLq+kRtSfQqe0x8R6LkZ3eS/BAUr3+OhsyUxb2CtS6cdjDAoPjBA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:56:26.472266Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.08989","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:62f8a80e5978adac0c4cea61400c2972a0d8cdc9667eae7751655d79bd511373","sha256:0a0f2a1e5f20ceb6c8b7696268150088f5be955365be12d4171360c097da4e54"],"state_sha256":"914499808eb471ea987996b98284275ea5428a499d6f577bf666f38b7bebeaa5"}