{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:WKFCDMIOFMQNJPEG42SXBKFLC7","short_pith_number":"pith:WKFCDMIO","schema_version":"1.0","canonical_sha256":"b28a21b10e2b20d4bc86e6a570a8ab17faee80e7ab39779687adb50541943ead","source":{"kind":"arxiv","id":"2305.10665","version":2},"attestation_state":"computed","paper":{"title":"Content-based Unrestricted Adversarial Attack","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CR"],"primary_cat":"cs.CV","authors_text":"Bo Li, Kaixun Jiang, Shouhong Ding, Shuang Wu, Wenqiang Zhang, Zhaoyu Chen","submitted_at":"2023-05-18T02:57:43Z","abstract_excerpt":"Unrestricted adversarial attacks typically manipulate the semantic content of an image (e.g., color or texture) to create adversarial examples that are both effective and photorealistic, demonstrating their ability to deceive human perception and deep neural networks with stealth and success. However, current works usually sacrifice unrestricted degrees and subjectively select some image content to guarantee the photorealism of unrestricted adversarial examples, which limits its attack performance. To ensure the photorealism of adversarial examples and boost attack performance, we propose a no"},"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":"2305.10665","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-05-18T02:57:43Z","cross_cats_sorted":["cs.AI","cs.CR"],"title_canon_sha256":"845bc9456ff11d3389256a90552b7c505a8d31dd71b92182e0bbd0557590fa26","abstract_canon_sha256":"240fb10556ad30bb5887f59f86183e5aa0edce2a67a4be3c2857c29388a73657"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:17:53.352302Z","signature_b64":"4qhcGU89XeY9jDoaNMYvvHroZ1edVVP7bxAfwGDGJ9rD38hBA+c5YxgzjQvJ2Mi7Tb1j5aZkZVejeHDd2K5vCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b28a21b10e2b20d4bc86e6a570a8ab17faee80e7ab39779687adb50541943ead","last_reissued_at":"2026-07-05T07:17:53.351790Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:17:53.351790Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Content-based Unrestricted Adversarial Attack","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CR"],"primary_cat":"cs.CV","authors_text":"Bo Li, Kaixun Jiang, Shouhong Ding, Shuang Wu, Wenqiang Zhang, Zhaoyu Chen","submitted_at":"2023-05-18T02:57:43Z","abstract_excerpt":"Unrestricted adversarial attacks typically manipulate the semantic content of an image (e.g., color or texture) to create adversarial examples that are both effective and photorealistic, demonstrating their ability to deceive human perception and deep neural networks with stealth and success. However, current works usually sacrifice unrestricted degrees and subjectively select some image content to guarantee the photorealism of unrestricted adversarial examples, which limits its attack performance. To ensure the photorealism of adversarial examples and boost attack performance, we propose a no"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.10665","kind":"arxiv","version":2},"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/2305.10665/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":"2305.10665","created_at":"2026-07-05T07:17:53.351848+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.10665v2","created_at":"2026-07-05T07:17:53.351848+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.10665","created_at":"2026-07-05T07:17:53.351848+00:00"},{"alias_kind":"pith_short_12","alias_value":"WKFCDMIOFMQN","created_at":"2026-07-05T07:17:53.351848+00:00"},{"alias_kind":"pith_short_16","alias_value":"WKFCDMIOFMQNJPEG","created_at":"2026-07-05T07:17:53.351848+00:00"},{"alias_kind":"pith_short_8","alias_value":"WKFCDMIO","created_at":"2026-07-05T07:17:53.351848+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.26566","citing_title":"Adversarial Diffusion Across Modalities: A Fusion Survey of Attacks, Defenses, and Evaluation for Text, Vision, and Vision-Language Models","ref_index":8,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WKFCDMIOFMQNJPEG42SXBKFLC7","json":"https://pith.science/pith/WKFCDMIOFMQNJPEG42SXBKFLC7.json","graph_json":"https://pith.science/api/pith-number/WKFCDMIOFMQNJPEG42SXBKFLC7/graph.json","events_json":"https://pith.science/api/pith-number/WKFCDMIOFMQNJPEG42SXBKFLC7/events.json","paper":"https://pith.science/paper/WKFCDMIO"},"agent_actions":{"view_html":"https://pith.science/pith/WKFCDMIOFMQNJPEG42SXBKFLC7","download_json":"https://pith.science/pith/WKFCDMIOFMQNJPEG42SXBKFLC7.json","view_paper":"https://pith.science/paper/WKFCDMIO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.10665&json=true","fetch_graph":"https://pith.science/api/pith-number/WKFCDMIOFMQNJPEG42SXBKFLC7/graph.json","fetch_events":"https://pith.science/api/pith-number/WKFCDMIOFMQNJPEG42SXBKFLC7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WKFCDMIOFMQNJPEG42SXBKFLC7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WKFCDMIOFMQNJPEG42SXBKFLC7/action/storage_attestation","attest_author":"https://pith.science/pith/WKFCDMIOFMQNJPEG42SXBKFLC7/action/author_attestation","sign_citation":"https://pith.science/pith/WKFCDMIOFMQNJPEG42SXBKFLC7/action/citation_signature","submit_replication":"https://pith.science/pith/WKFCDMIOFMQNJPEG42SXBKFLC7/action/replication_record"}},"created_at":"2026-07-05T07:17:53.351848+00:00","updated_at":"2026-07-05T07:17:53.351848+00:00"}