{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:W5ETRDXDLJVFZTJ6P7OXCFGVUG","short_pith_number":"pith:W5ETRDXD","schema_version":"1.0","canonical_sha256":"b749388ee35a6a5ccd3e7fdd7114d5a1ab084ee81aa1684aba11b9909fe1e1ab","source":{"kind":"arxiv","id":"2405.06865","version":1},"attestation_state":"computed","paper":{"title":"Disrupting Style Mimicry Attacks on Video Imagery","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CR"],"primary_cat":"cs.CV","authors_text":"Ben Y. Zhao, Haitao Zheng, Josephine Passananti, Shawn Shan, Stanley Wu","submitted_at":"2024-05-11T01:40:19Z","abstract_excerpt":"Generative AI models are often used to perform mimicry attacks, where a pretrained model is fine-tuned on a small sample of images to learn to mimic a specific artist of interest. While researchers have introduced multiple anti-mimicry protection tools (Mist, Glaze, Anti-Dreambooth), recent evidence points to a growing trend of mimicry models using videos as sources of training data. This paper presents our experiences exploring techniques to disrupt style mimicry on video imagery. We first validate that mimicry attacks can succeed by training on individual frames extracted from videos. We sho"},"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":"2405.06865","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-11T01:40:19Z","cross_cats_sorted":["cs.CR"],"title_canon_sha256":"e624fb169500ad6641f225f429f1907636c36d15969db98346d587760e6f432c","abstract_canon_sha256":"7d1f6572805643ad5cf927e931e67de8fabef6d901d91f1c88357a9da27c9b02"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:18:12.917929Z","signature_b64":"NacZqPkC6qhvKCKSEgMsg+NTIS2p/rbMFUmtgHbFjpMiY1NNcJmAbad+CrgQDgqNwhNWrb787m9D65JZcoPuAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b749388ee35a6a5ccd3e7fdd7114d5a1ab084ee81aa1684aba11b9909fe1e1ab","last_reissued_at":"2026-07-05T08:18:12.917444Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:18:12.917444Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Disrupting Style Mimicry Attacks on Video Imagery","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CR"],"primary_cat":"cs.CV","authors_text":"Ben Y. Zhao, Haitao Zheng, Josephine Passananti, Shawn Shan, Stanley Wu","submitted_at":"2024-05-11T01:40:19Z","abstract_excerpt":"Generative AI models are often used to perform mimicry attacks, where a pretrained model is fine-tuned on a small sample of images to learn to mimic a specific artist of interest. While researchers have introduced multiple anti-mimicry protection tools (Mist, Glaze, Anti-Dreambooth), recent evidence points to a growing trend of mimicry models using videos as sources of training data. This paper presents our experiences exploring techniques to disrupt style mimicry on video imagery. We first validate that mimicry attacks can succeed by training on individual frames extracted from videos. We sho"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.06865","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/2405.06865/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":"2405.06865","created_at":"2026-07-05T08:18:12.917506+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.06865v1","created_at":"2026-07-05T08:18:12.917506+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.06865","created_at":"2026-07-05T08:18:12.917506+00:00"},{"alias_kind":"pith_short_12","alias_value":"W5ETRDXDLJVF","created_at":"2026-07-05T08:18:12.917506+00:00"},{"alias_kind":"pith_short_16","alias_value":"W5ETRDXDLJVFZTJ6","created_at":"2026-07-05T08:18:12.917506+00:00"},{"alias_kind":"pith_short_8","alias_value":"W5ETRDXD","created_at":"2026-07-05T08:18:12.917506+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/W5ETRDXDLJVFZTJ6P7OXCFGVUG","json":"https://pith.science/pith/W5ETRDXDLJVFZTJ6P7OXCFGVUG.json","graph_json":"https://pith.science/api/pith-number/W5ETRDXDLJVFZTJ6P7OXCFGVUG/graph.json","events_json":"https://pith.science/api/pith-number/W5ETRDXDLJVFZTJ6P7OXCFGVUG/events.json","paper":"https://pith.science/paper/W5ETRDXD"},"agent_actions":{"view_html":"https://pith.science/pith/W5ETRDXDLJVFZTJ6P7OXCFGVUG","download_json":"https://pith.science/pith/W5ETRDXDLJVFZTJ6P7OXCFGVUG.json","view_paper":"https://pith.science/paper/W5ETRDXD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.06865&json=true","fetch_graph":"https://pith.science/api/pith-number/W5ETRDXDLJVFZTJ6P7OXCFGVUG/graph.json","fetch_events":"https://pith.science/api/pith-number/W5ETRDXDLJVFZTJ6P7OXCFGVUG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/W5ETRDXDLJVFZTJ6P7OXCFGVUG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/W5ETRDXDLJVFZTJ6P7OXCFGVUG/action/storage_attestation","attest_author":"https://pith.science/pith/W5ETRDXDLJVFZTJ6P7OXCFGVUG/action/author_attestation","sign_citation":"https://pith.science/pith/W5ETRDXDLJVFZTJ6P7OXCFGVUG/action/citation_signature","submit_replication":"https://pith.science/pith/W5ETRDXDLJVFZTJ6P7OXCFGVUG/action/replication_record"}},"created_at":"2026-07-05T08:18:12.917506+00:00","updated_at":"2026-07-05T08:18:12.917506+00:00"}