{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:VYNUHRDKVLKCP5U27A3COHN5KL","short_pith_number":"pith:VYNUHRDK","canonical_record":{"source":{"id":"2312.03030","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-05T11:07:39Z","cross_cats_sorted":[],"title_canon_sha256":"60a51691edfa3c29a6723b7ab1cc78d56208202c490031bade8dd6187a40f9a1","abstract_canon_sha256":"8522ef154aa7a645a467246c3b7050204784593e9e0de6589599b5a15cfad36a"},"schema_version":"1.0"},"canonical_sha256":"ae1b43c46aaad427f69af836271dbd52ce1250980a4fb4cc895dcbf9f9d7f2ca","source":{"kind":"arxiv","id":"2312.03030","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.03030","created_at":"2026-07-05T07:20:57Z"},{"alias_kind":"arxiv_version","alias_value":"2312.03030v1","created_at":"2026-07-05T07:20:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.03030","created_at":"2026-07-05T07:20:57Z"},{"alias_kind":"pith_short_12","alias_value":"VYNUHRDKVLKC","created_at":"2026-07-05T07:20:57Z"},{"alias_kind":"pith_short_16","alias_value":"VYNUHRDKVLKCP5U2","created_at":"2026-07-05T07:20:57Z"},{"alias_kind":"pith_short_8","alias_value":"VYNUHRDK","created_at":"2026-07-05T07:20:57Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:VYNUHRDKVLKCP5U27A3COHN5KL","target":"record","payload":{"canonical_record":{"source":{"id":"2312.03030","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-05T11:07:39Z","cross_cats_sorted":[],"title_canon_sha256":"60a51691edfa3c29a6723b7ab1cc78d56208202c490031bade8dd6187a40f9a1","abstract_canon_sha256":"8522ef154aa7a645a467246c3b7050204784593e9e0de6589599b5a15cfad36a"},"schema_version":"1.0"},"canonical_sha256":"ae1b43c46aaad427f69af836271dbd52ce1250980a4fb4cc895dcbf9f9d7f2ca","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:20:57.207226Z","signature_b64":"RxPKWAoRrE5ELPaZfPOeyzYMw7T2wKREBMNLY3k34vBKGE9ISxUlOprVPBstoQlQwKb5k7QpAvh0FYpdpYdJCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ae1b43c46aaad427f69af836271dbd52ce1250980a4fb4cc895dcbf9f9d7f2ca","last_reissued_at":"2026-07-05T07:20:57.206765Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:20:57.206765Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2312.03030","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":"2026-07-05T07:20:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"a70hb49o0/RoXMl5u/fnhnYlpAsTCi+/6cdhYwXH+gU07RNrtv64iywMkv7OUW465yp4vHgh9N5RYK9hzzbMCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T11:03:25.399265Z"},"content_sha256":"33f4d1eb2388b66d318a823de0017aa67e396a56fb23c777eb903f16837b8565","schema_version":"1.0","event_id":"sha256:33f4d1eb2388b66d318a823de0017aa67e396a56fb23c777eb903f16837b8565"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:VYNUHRDKVLKCP5U27A3COHN5KL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Generating Visually Realistic Adversarial Patch","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Kunyu Wang, Xiaosen Wang","submitted_at":"2023-12-05T11:07:39Z","abstract_excerpt":"Deep neural networks (DNNs) are vulnerable to various types of adversarial examples, bringing huge threats to security-critical applications. Among these, adversarial patches have drawn increasing attention due to their good applicability to fool DNNs in the physical world. However, existing works often generate patches with meaningless noise or patterns, making it conspicuous to humans. To address this issue, we explore how to generate visually realistic adversarial patches to fool DNNs. Firstly, we analyze that a high-quality adversarial patch should be realistic, position irrelevant, and pr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.03030","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/2312.03030/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":"2026-07-05T07:20:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MQVDBmgHTderFFGE4yLpplP7xJ4o5MXr/6TZRo/hwPYRDSKThKMN8ykPIcbE/9PiCqYsIcV7YUkbD2MoA91/Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T11:03:25.399790Z"},"content_sha256":"6f9cb8ff858f217bc84d9f380de3aca434a6f4bd41ff665f81acb723a437a6fa","schema_version":"1.0","event_id":"sha256:6f9cb8ff858f217bc84d9f380de3aca434a6f4bd41ff665f81acb723a437a6fa"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VYNUHRDKVLKCP5U27A3COHN5KL/bundle.json","state_url":"https://pith.science/pith/VYNUHRDKVLKCP5U27A3COHN5KL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VYNUHRDKVLKCP5U27A3COHN5KL/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":"2026-08-10T11:03:25Z","links":{"resolver":"https://pith.science/pith/VYNUHRDKVLKCP5U27A3COHN5KL","bundle":"https://pith.science/pith/VYNUHRDKVLKCP5U27A3COHN5KL/bundle.json","state":"https://pith.science/pith/VYNUHRDKVLKCP5U27A3COHN5KL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VYNUHRDKVLKCP5U27A3COHN5KL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:VYNUHRDKVLKCP5U27A3COHN5KL","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":"8522ef154aa7a645a467246c3b7050204784593e9e0de6589599b5a15cfad36a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-05T11:07:39Z","title_canon_sha256":"60a51691edfa3c29a6723b7ab1cc78d56208202c490031bade8dd6187a40f9a1"},"schema_version":"1.0","source":{"id":"2312.03030","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.03030","created_at":"2026-07-05T07:20:57Z"},{"alias_kind":"arxiv_version","alias_value":"2312.03030v1","created_at":"2026-07-05T07:20:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.03030","created_at":"2026-07-05T07:20:57Z"},{"alias_kind":"pith_short_12","alias_value":"VYNUHRDKVLKC","created_at":"2026-07-05T07:20:57Z"},{"alias_kind":"pith_short_16","alias_value":"VYNUHRDKVLKCP5U2","created_at":"2026-07-05T07:20:57Z"},{"alias_kind":"pith_short_8","alias_value":"VYNUHRDK","created_at":"2026-07-05T07:20:57Z"}],"graph_snapshots":[{"event_id":"sha256:6f9cb8ff858f217bc84d9f380de3aca434a6f4bd41ff665f81acb723a437a6fa","target":"graph","created_at":"2026-07-05T07:20:57Z","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/2312.03030/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Deep neural networks (DNNs) are vulnerable to various types of adversarial examples, bringing huge threats to security-critical applications. Among these, adversarial patches have drawn increasing attention due to their good applicability to fool DNNs in the physical world. However, existing works often generate patches with meaningless noise or patterns, making it conspicuous to humans. To address this issue, we explore how to generate visually realistic adversarial patches to fool DNNs. Firstly, we analyze that a high-quality adversarial patch should be realistic, position irrelevant, and pr","authors_text":"Kunyu Wang, Xiaosen Wang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-05T11:07:39Z","title":"Generating Visually Realistic Adversarial Patch"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.03030","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":"sha256:33f4d1eb2388b66d318a823de0017aa67e396a56fb23c777eb903f16837b8565","target":"record","created_at":"2026-07-05T07:20:57Z","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":"8522ef154aa7a645a467246c3b7050204784593e9e0de6589599b5a15cfad36a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-05T11:07:39Z","title_canon_sha256":"60a51691edfa3c29a6723b7ab1cc78d56208202c490031bade8dd6187a40f9a1"},"schema_version":"1.0","source":{"id":"2312.03030","kind":"arxiv","version":1}},"canonical_sha256":"ae1b43c46aaad427f69af836271dbd52ce1250980a4fb4cc895dcbf9f9d7f2ca","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ae1b43c46aaad427f69af836271dbd52ce1250980a4fb4cc895dcbf9f9d7f2ca","first_computed_at":"2026-07-05T07:20:57.206765Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:20:57.206765Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"RxPKWAoRrE5ELPaZfPOeyzYMw7T2wKREBMNLY3k34vBKGE9ISxUlOprVPBstoQlQwKb5k7QpAvh0FYpdpYdJCw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:20:57.207226Z","signed_message":"canonical_sha256_bytes"},"source_id":"2312.03030","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:33f4d1eb2388b66d318a823de0017aa67e396a56fb23c777eb903f16837b8565","sha256:6f9cb8ff858f217bc84d9f380de3aca434a6f4bd41ff665f81acb723a437a6fa"],"state_sha256":"fbca54a00c31062c7618ea48603da3605bf3d3c1cf01385127d03642313949e6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DPJyY1iL/B6Yr6b/ucXU1VQ2ITmK2UukcHD78REXmYjTde+iKiIocsaSJTWugdKG8BwXUVgC6sPuBl1+wvhlBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T11:03:25.404289Z","bundle_sha256":"04e89209d5b6c7545db7c717e692fe730242d9129c0d0fd96a003ae8018d59d4"}}