{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:NJZEQ2W5CP72OWQDXVDZSWJGAY","short_pith_number":"pith:NJZEQ2W5","schema_version":"1.0","canonical_sha256":"6a72486add13ffa75a03bd4799592606079c33b8b3219dd3881044dafe954064","source":{"kind":"arxiv","id":"2306.01902","version":2},"attestation_state":"computed","paper":{"title":"Unlearnable Examples for Diffusion Models: Protect Data from Unauthorized Exploitation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chenan Wang, Jinhao Duan, Kaidi Xu, Qi Guo, Rui Zhang, Xing Hu, Yunji Chen, Zhengyue Zhao, Zidong Du","submitted_at":"2023-06-02T20:19:19Z","abstract_excerpt":"Diffusion models have demonstrated remarkable performance in image generation tasks, paving the way for powerful AIGC applications. However, these widely-used generative models can also raise security and privacy concerns, such as copyright infringement, and sensitive data leakage. To tackle these issues, we propose a method, Unlearnable Diffusion Perturbation, to safeguard images from unauthorized exploitation. Our approach involves designing an algorithm to generate sample-wise perturbation noise for each image to be protected. This imperceptible protective noise makes the data almost unlear"},"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":"2306.01902","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-06-02T20:19:19Z","cross_cats_sorted":[],"title_canon_sha256":"77e6fcdca7e16696d9853d88eec95bd6192a71700daa4ed7fc583273cd6ffe0b","abstract_canon_sha256":"a8d756b7dc2476a6856547fc39cf21690d1b7c845d667e326496e041c3a6a5b3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:35:35.369853Z","signature_b64":"YKaDI9ioLosyCuN8mptcCpnhzJ4EPt/jF820M4MUwc9IdA2tO+8d86+6nza1qJjPtb4miLnzYDExwFKOHuXcAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6a72486add13ffa75a03bd4799592606079c33b8b3219dd3881044dafe954064","last_reissued_at":"2026-07-05T08:35:35.369438Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:35:35.369438Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Unlearnable Examples for Diffusion Models: Protect Data from Unauthorized Exploitation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chenan Wang, Jinhao Duan, Kaidi Xu, Qi Guo, Rui Zhang, Xing Hu, Yunji Chen, Zhengyue Zhao, Zidong Du","submitted_at":"2023-06-02T20:19:19Z","abstract_excerpt":"Diffusion models have demonstrated remarkable performance in image generation tasks, paving the way for powerful AIGC applications. However, these widely-used generative models can also raise security and privacy concerns, such as copyright infringement, and sensitive data leakage. To tackle these issues, we propose a method, Unlearnable Diffusion Perturbation, to safeguard images from unauthorized exploitation. Our approach involves designing an algorithm to generate sample-wise perturbation noise for each image to be protected. This imperceptible protective noise makes the data almost unlear"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.01902","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/2306.01902/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":"2306.01902","created_at":"2026-07-05T08:35:35.369500+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.01902v2","created_at":"2026-07-05T08:35:35.369500+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.01902","created_at":"2026-07-05T08:35:35.369500+00:00"},{"alias_kind":"pith_short_12","alias_value":"NJZEQ2W5CP72","created_at":"2026-07-05T08:35:35.369500+00:00"},{"alias_kind":"pith_short_16","alias_value":"NJZEQ2W5CP72OWQD","created_at":"2026-07-05T08:35:35.369500+00:00"},{"alias_kind":"pith_short_8","alias_value":"NJZEQ2W5","created_at":"2026-07-05T08:35:35.369500+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.12263","citing_title":"VOID: Defeating Unauthorized Mimicry in Latent Diffusion Models","ref_index":74,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14291","citing_title":"To See is Not to Learn: Protecting Multimodal Data from Unauthorized Fine-Tuning of Large Vision-Language Model","ref_index":71,"is_internal_anchor":false},{"citing_arxiv_id":"2604.14570","citing_title":"Deepfake Detection Generalization with Diffusion Noise","ref_index":82,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NJZEQ2W5CP72OWQDXVDZSWJGAY","json":"https://pith.science/pith/NJZEQ2W5CP72OWQDXVDZSWJGAY.json","graph_json":"https://pith.science/api/pith-number/NJZEQ2W5CP72OWQDXVDZSWJGAY/graph.json","events_json":"https://pith.science/api/pith-number/NJZEQ2W5CP72OWQDXVDZSWJGAY/events.json","paper":"https://pith.science/paper/NJZEQ2W5"},"agent_actions":{"view_html":"https://pith.science/pith/NJZEQ2W5CP72OWQDXVDZSWJGAY","download_json":"https://pith.science/pith/NJZEQ2W5CP72OWQDXVDZSWJGAY.json","view_paper":"https://pith.science/paper/NJZEQ2W5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.01902&json=true","fetch_graph":"https://pith.science/api/pith-number/NJZEQ2W5CP72OWQDXVDZSWJGAY/graph.json","fetch_events":"https://pith.science/api/pith-number/NJZEQ2W5CP72OWQDXVDZSWJGAY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NJZEQ2W5CP72OWQDXVDZSWJGAY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NJZEQ2W5CP72OWQDXVDZSWJGAY/action/storage_attestation","attest_author":"https://pith.science/pith/NJZEQ2W5CP72OWQDXVDZSWJGAY/action/author_attestation","sign_citation":"https://pith.science/pith/NJZEQ2W5CP72OWQDXVDZSWJGAY/action/citation_signature","submit_replication":"https://pith.science/pith/NJZEQ2W5CP72OWQDXVDZSWJGAY/action/replication_record"}},"created_at":"2026-07-05T08:35:35.369500+00:00","updated_at":"2026-07-05T08:35:35.369500+00:00"}