{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:K2CVWKFDJ3F3SGBVSYORMESRCV","short_pith_number":"pith:K2CVWKFD","schema_version":"1.0","canonical_sha256":"56855b28a34ecbb91835961d161251155457ae3d5690c98d88d486fda03d9c4d","source":{"kind":"arxiv","id":"2302.04578","version":2},"attestation_state":"computed","paper":{"title":"Adversarial Example Does Good: Preventing Painting Imitation from Diffusion Models via Adversarial Examples","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CR","cs.LG"],"primary_cat":"cs.CV","authors_text":"Chumeng Liang, Haibing Guan, Jiaru Zhang, Ruhui Ma, Tao Song, Xiaoyu Wu, Yang Hua, Yiming Xue, Zhengui Xue","submitted_at":"2023-02-09T11:36:39Z","abstract_excerpt":"Recently, Diffusion Models (DMs) boost a wave in AI for Art yet raise new copyright concerns, where infringers benefit from using unauthorized paintings to train DMs to generate novel paintings in a similar style. To address these emerging copyright violations, in this paper, we are the first to explore and propose to utilize adversarial examples for DMs to protect human-created artworks. Specifically, we first build a theoretical framework to define and evaluate the adversarial examples for DMs. Then, based on this framework, we design a novel algorithm, named AdvDM, which exploits a Monte-Ca"},"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":"2302.04578","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-02-09T11:36:39Z","cross_cats_sorted":["cs.AI","cs.CR","cs.LG"],"title_canon_sha256":"b9e45e4b5a4eeb6db9b74c0ed82ef27bc9ed2883ff11a0516f6d8507e04b8c0f","abstract_canon_sha256":"6b61a8bf9aadf1db193484c2737e4574bccfe387458c825ef9bbd86d24ca7049"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:17:46.142195Z","signature_b64":"60KZ/fo07yNHs3VmJnIiGSvhw5Uk/RnwApa8OzzDbs5kCuUobueh1icoADEHtGLhH2XeZa7H9bKxFnbSL75AAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"56855b28a34ecbb91835961d161251155457ae3d5690c98d88d486fda03d9c4d","last_reissued_at":"2026-07-05T06:17:46.141728Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:17:46.141728Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Adversarial Example Does Good: Preventing Painting Imitation from Diffusion Models via Adversarial Examples","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CR","cs.LG"],"primary_cat":"cs.CV","authors_text":"Chumeng Liang, Haibing Guan, Jiaru Zhang, Ruhui Ma, Tao Song, Xiaoyu Wu, Yang Hua, Yiming Xue, Zhengui Xue","submitted_at":"2023-02-09T11:36:39Z","abstract_excerpt":"Recently, Diffusion Models (DMs) boost a wave in AI for Art yet raise new copyright concerns, where infringers benefit from using unauthorized paintings to train DMs to generate novel paintings in a similar style. To address these emerging copyright violations, in this paper, we are the first to explore and propose to utilize adversarial examples for DMs to protect human-created artworks. Specifically, we first build a theoretical framework to define and evaluate the adversarial examples for DMs. Then, based on this framework, we design a novel algorithm, named AdvDM, which exploits a Monte-Ca"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.04578","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/2302.04578/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":"2302.04578","created_at":"2026-07-05T06:17:46.141795+00:00"},{"alias_kind":"arxiv_version","alias_value":"2302.04578v2","created_at":"2026-07-05T06:17:46.141795+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.04578","created_at":"2026-07-05T06:17:46.141795+00:00"},{"alias_kind":"pith_short_12","alias_value":"K2CVWKFDJ3F3","created_at":"2026-07-05T06:17:46.141795+00:00"},{"alias_kind":"pith_short_16","alias_value":"K2CVWKFDJ3F3SGBV","created_at":"2026-07-05T06:17:46.141795+00:00"},{"alias_kind":"pith_short_8","alias_value":"K2CVWKFD","created_at":"2026-07-05T06:17:46.141795+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.02038","citing_title":"Hierarchical Anti-Aesthetics: Protecting Facial Privacy against Customized Diffusion Models","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2606.12263","citing_title":"VOID: Defeating Unauthorized Mimicry in Latent Diffusion Models","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2606.09909","citing_title":"Bypassing Copyright Protection in Diffusion-based Customization via Two-Stage Latent Feature Optimization","ref_index":19,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/K2CVWKFDJ3F3SGBVSYORMESRCV","json":"https://pith.science/pith/K2CVWKFDJ3F3SGBVSYORMESRCV.json","graph_json":"https://pith.science/api/pith-number/K2CVWKFDJ3F3SGBVSYORMESRCV/graph.json","events_json":"https://pith.science/api/pith-number/K2CVWKFDJ3F3SGBVSYORMESRCV/events.json","paper":"https://pith.science/paper/K2CVWKFD"},"agent_actions":{"view_html":"https://pith.science/pith/K2CVWKFDJ3F3SGBVSYORMESRCV","download_json":"https://pith.science/pith/K2CVWKFDJ3F3SGBVSYORMESRCV.json","view_paper":"https://pith.science/paper/K2CVWKFD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2302.04578&json=true","fetch_graph":"https://pith.science/api/pith-number/K2CVWKFDJ3F3SGBVSYORMESRCV/graph.json","fetch_events":"https://pith.science/api/pith-number/K2CVWKFDJ3F3SGBVSYORMESRCV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/K2CVWKFDJ3F3SGBVSYORMESRCV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/K2CVWKFDJ3F3SGBVSYORMESRCV/action/storage_attestation","attest_author":"https://pith.science/pith/K2CVWKFDJ3F3SGBVSYORMESRCV/action/author_attestation","sign_citation":"https://pith.science/pith/K2CVWKFDJ3F3SGBVSYORMESRCV/action/citation_signature","submit_replication":"https://pith.science/pith/K2CVWKFDJ3F3SGBVSYORMESRCV/action/replication_record"}},"created_at":"2026-07-05T06:17:46.141795+00:00","updated_at":"2026-07-05T06:17:46.141795+00:00"}