{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:BW3CHAY5DYSMZYUZUNH57VU2OJ","short_pith_number":"pith:BW3CHAY5","schema_version":"1.0","canonical_sha256":"0db623831d1e24cce299a34fdfd69a72610322da7e6005abc57c150fde416238","source":{"kind":"arxiv","id":"2307.08076","version":1},"attestation_state":"computed","paper":{"title":"Diffusion to Confusion: Naturalistic Adversarial Patch Generation Based on Diffusion Model for Object Detector","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Che-Hsien Lin, Ernie Chu, Jia-Ching Wang, Jun-Cheng Chen, Shuo-Yen Lin","submitted_at":"2023-07-16T15:22:30Z","abstract_excerpt":"Many physical adversarial patch generation methods are widely proposed to protect personal privacy from malicious monitoring using object detectors. However, they usually fail to generate satisfactory patch images in terms of both stealthiness and attack performance without making huge efforts on careful hyperparameter tuning. To address this issue, we propose a novel naturalistic adversarial patch generation method based on the diffusion models (DM). Through sampling the optimal image from the DM model pretrained upon natural images, it allows us to stably craft high-quality and naturalistic "},"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":"2307.08076","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-07-16T15:22:30Z","cross_cats_sorted":[],"title_canon_sha256":"fbc6429250ee5506e28359f37159150d17b224a1dfaf680f38bea150a916b26f","abstract_canon_sha256":"bc3bae547fd886c621618d70875abd9260bfd404e5906d53c88edcc1c905d2bf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:31:19.758239Z","signature_b64":"i/aemHUxNymG6hGH4vAd1S76Vjdrp253JkJcyTpuKqp0kWrlS3ZM2KGCwyl7G7/zIc7em8D7Aadc7mykffYHCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0db623831d1e24cce299a34fdfd69a72610322da7e6005abc57c150fde416238","last_reissued_at":"2026-07-05T06:31:19.757853Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:31:19.757853Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Diffusion to Confusion: Naturalistic Adversarial Patch Generation Based on Diffusion Model for Object Detector","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Che-Hsien Lin, Ernie Chu, Jia-Ching Wang, Jun-Cheng Chen, Shuo-Yen Lin","submitted_at":"2023-07-16T15:22:30Z","abstract_excerpt":"Many physical adversarial patch generation methods are widely proposed to protect personal privacy from malicious monitoring using object detectors. However, they usually fail to generate satisfactory patch images in terms of both stealthiness and attack performance without making huge efforts on careful hyperparameter tuning. To address this issue, we propose a novel naturalistic adversarial patch generation method based on the diffusion models (DM). Through sampling the optimal image from the DM model pretrained upon natural images, it allows us to stably craft high-quality and naturalistic "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.08076","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/2307.08076/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":"2307.08076","created_at":"2026-07-05T06:31:19.757915+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.08076v1","created_at":"2026-07-05T06:31:19.757915+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.08076","created_at":"2026-07-05T06:31:19.757915+00:00"},{"alias_kind":"pith_short_12","alias_value":"BW3CHAY5DYSM","created_at":"2026-07-05T06:31:19.757915+00:00"},{"alias_kind":"pith_short_16","alias_value":"BW3CHAY5DYSMZYUZ","created_at":"2026-07-05T06:31:19.757915+00:00"},{"alias_kind":"pith_short_8","alias_value":"BW3CHAY5","created_at":"2026-07-05T06:31:19.757915+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.18591","citing_title":"SpaNN: Detecting Multiple Adversarial Patches on CNNs by Spanning Saliency Thresholds","ref_index":36,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BW3CHAY5DYSMZYUZUNH57VU2OJ","json":"https://pith.science/pith/BW3CHAY5DYSMZYUZUNH57VU2OJ.json","graph_json":"https://pith.science/api/pith-number/BW3CHAY5DYSMZYUZUNH57VU2OJ/graph.json","events_json":"https://pith.science/api/pith-number/BW3CHAY5DYSMZYUZUNH57VU2OJ/events.json","paper":"https://pith.science/paper/BW3CHAY5"},"agent_actions":{"view_html":"https://pith.science/pith/BW3CHAY5DYSMZYUZUNH57VU2OJ","download_json":"https://pith.science/pith/BW3CHAY5DYSMZYUZUNH57VU2OJ.json","view_paper":"https://pith.science/paper/BW3CHAY5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.08076&json=true","fetch_graph":"https://pith.science/api/pith-number/BW3CHAY5DYSMZYUZUNH57VU2OJ/graph.json","fetch_events":"https://pith.science/api/pith-number/BW3CHAY5DYSMZYUZUNH57VU2OJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BW3CHAY5DYSMZYUZUNH57VU2OJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BW3CHAY5DYSMZYUZUNH57VU2OJ/action/storage_attestation","attest_author":"https://pith.science/pith/BW3CHAY5DYSMZYUZUNH57VU2OJ/action/author_attestation","sign_citation":"https://pith.science/pith/BW3CHAY5DYSMZYUZUNH57VU2OJ/action/citation_signature","submit_replication":"https://pith.science/pith/BW3CHAY5DYSMZYUZUNH57VU2OJ/action/replication_record"}},"created_at":"2026-07-05T06:31:19.757915+00:00","updated_at":"2026-07-05T06:31:19.757915+00:00"}