{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:P4W2HKKQ7WZGJV7QJNYLENKKRK","short_pith_number":"pith:P4W2HKKQ","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"},"canonical_sha256":"7f2da3a950fdb264d7f04b70b2354a8a907928ecff101be0127b4704bb1ce1ab","source":{"kind":"arxiv","id":"2408.08989","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:P4W2HKKQ7WZGJV7QJNYLENKKRK","target":"record","payload":{"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"},"canonical_sha256":"7f2da3a950fdb264d7f04b70b2354a8a907928ecff101be0127b4704bb1ce1ab","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"},"source_kind":"arxiv","source_id":"2408.08989","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:56:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GIm+BJ+pl+mwb7LVMkNjLyy4Bw4no+ssK40ZOvVdFvHil/IFm1D38ABw4vSB+B2uDjCmipJ8JsE0jWdTdCBeAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T16:55:37.496547Z"},"content_sha256":"62f8a80e5978adac0c4cea61400c2972a0d8cdc9667eae7751655d79bd511373","schema_version":"1.0","event_id":"sha256:62f8a80e5978adac0c4cea61400c2972a0d8cdc9667eae7751655d79bd511373"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:P4W2HKKQ7WZGJV7QJNYLENKKRK","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:56:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ce1B3wKrteIHYMtuO4UPzxjMA0UdxvwNkQx2ns7GWBRUPnhtk4yv1X547y9bqISaXxoojq2DUYm1v2ztNKvOBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T16:55:37.497083Z"},"content_sha256":"0a0f2a1e5f20ceb6c8b7696268150088f5be955365be12d4171360c097da4e54","schema_version":"1.0","event_id":"sha256:0a0f2a1e5f20ceb6c8b7696268150088f5be955365be12d4171360c097da4e54"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/P4W2HKKQ7WZGJV7QJNYLENKKRK/bundle.json","state_url":"https://pith.science/pith/P4W2HKKQ7WZGJV7QJNYLENKKRK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/P4W2HKKQ7WZGJV7QJNYLENKKRK/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-20T16:55:37Z","links":{"resolver":"https://pith.science/pith/P4W2HKKQ7WZGJV7QJNYLENKKRK","bundle":"https://pith.science/pith/P4W2HKKQ7WZGJV7QJNYLENKKRK/bundle.json","state":"https://pith.science/pith/P4W2HKKQ7WZGJV7QJNYLENKKRK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/P4W2HKKQ7WZGJV7QJNYLENKKRK/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gGPyfo3gzrKSlh/1VFtUUnVaI/AIMu0Pvejdwp8hXdHxNprCXYPFBpss93634RLeCWMcy9tbXRxaZ5ZOFCqDDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-20T16:55:37.501301Z","bundle_sha256":"8add048c28371cd5c61e7c68c75681838905b912ffabaae23e97f24d2edba44b"}}