{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:UK5P3RIRXOQTVGSM2KWC6SVROJ","short_pith_number":"pith:UK5P3RIR","schema_version":"1.0","canonical_sha256":"a2bafdc511bba13a9a4cd2ac2f4ab1727d904ac7038f4d25a75f6bda99869a91","source":{"kind":"arxiv","id":"2312.16401","version":1},"attestation_state":"computed","paper":{"title":"Natural Adversarial Patch Generation Method Based on Latent Diffusion Model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dong Jiang, Fazhan Liu, Kai Yan, Xianyi Chen","submitted_at":"2023-12-27T04:09:44Z","abstract_excerpt":"Recently, some research show that deep neural networks are vulnerable to the adversarial attacks, the well-trainned samples or patches could be used to trick the neural network detector or human visual perception. However, these adversarial patches, with their conspicuous and unusual patterns, lack camouflage and can easily raise suspicion in the real world. To solve this problem, this paper proposed a novel adversarial patch method called the Latent Diffusion Patch (LDP), in which, a pretrained encoder is first designed to compress the natural images into a feature space with key characterist"},"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":"2312.16401","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-27T04:09:44Z","cross_cats_sorted":[],"title_canon_sha256":"1bc4ae463ea220ffebc6108844092359ee08e717e2f2439777a8457c9f3dc97f","abstract_canon_sha256":"83d0d1ed03f21642c681993dc09dc1649c5b069a3f6d37a8f2a5abf0c7543bc6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:28:16.763621Z","signature_b64":"Nku5WRJBVuPjCgCMGqrZBn7NsPgimb9Qwy/PiDfF/nDNgisdInBnuIO9daJq8mFKwtUWRz62PSGNuUrSrq0PBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a2bafdc511bba13a9a4cd2ac2f4ab1727d904ac7038f4d25a75f6bda99869a91","last_reissued_at":"2026-07-05T07:28:16.763204Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:28:16.763204Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Natural Adversarial Patch Generation Method Based on Latent Diffusion Model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dong Jiang, Fazhan Liu, Kai Yan, Xianyi Chen","submitted_at":"2023-12-27T04:09:44Z","abstract_excerpt":"Recently, some research show that deep neural networks are vulnerable to the adversarial attacks, the well-trainned samples or patches could be used to trick the neural network detector or human visual perception. However, these adversarial patches, with their conspicuous and unusual patterns, lack camouflage and can easily raise suspicion in the real world. To solve this problem, this paper proposed a novel adversarial patch method called the Latent Diffusion Patch (LDP), in which, a pretrained encoder is first designed to compress the natural images into a feature space with key characterist"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.16401","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/2312.16401/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":"2312.16401","created_at":"2026-07-05T07:28:16.763253+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.16401v1","created_at":"2026-07-05T07:28:16.763253+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.16401","created_at":"2026-07-05T07:28:16.763253+00:00"},{"alias_kind":"pith_short_12","alias_value":"UK5P3RIRXOQT","created_at":"2026-07-05T07:28:16.763253+00:00"},{"alias_kind":"pith_short_16","alias_value":"UK5P3RIRXOQTVGSM","created_at":"2026-07-05T07:28:16.763253+00:00"},{"alias_kind":"pith_short_8","alias_value":"UK5P3RIR","created_at":"2026-07-05T07:28:16.763253+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":7,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UK5P3RIRXOQTVGSM2KWC6SVROJ","json":"https://pith.science/pith/UK5P3RIRXOQTVGSM2KWC6SVROJ.json","graph_json":"https://pith.science/api/pith-number/UK5P3RIRXOQTVGSM2KWC6SVROJ/graph.json","events_json":"https://pith.science/api/pith-number/UK5P3RIRXOQTVGSM2KWC6SVROJ/events.json","paper":"https://pith.science/paper/UK5P3RIR"},"agent_actions":{"view_html":"https://pith.science/pith/UK5P3RIRXOQTVGSM2KWC6SVROJ","download_json":"https://pith.science/pith/UK5P3RIRXOQTVGSM2KWC6SVROJ.json","view_paper":"https://pith.science/paper/UK5P3RIR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.16401&json=true","fetch_graph":"https://pith.science/api/pith-number/UK5P3RIRXOQTVGSM2KWC6SVROJ/graph.json","fetch_events":"https://pith.science/api/pith-number/UK5P3RIRXOQTVGSM2KWC6SVROJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UK5P3RIRXOQTVGSM2KWC6SVROJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UK5P3RIRXOQTVGSM2KWC6SVROJ/action/storage_attestation","attest_author":"https://pith.science/pith/UK5P3RIRXOQTVGSM2KWC6SVROJ/action/author_attestation","sign_citation":"https://pith.science/pith/UK5P3RIRXOQTVGSM2KWC6SVROJ/action/citation_signature","submit_replication":"https://pith.science/pith/UK5P3RIRXOQTVGSM2KWC6SVROJ/action/replication_record"}},"created_at":"2026-07-05T07:28:16.763253+00:00","updated_at":"2026-07-05T07:28:16.763253+00:00"}