{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:ZQR4CGUUZBZLZ6PPUZ5F543QOE","short_pith_number":"pith:ZQR4CGUU","schema_version":"1.0","canonical_sha256":"cc23c11a94c872bcf9efa67a5ef37071065cf600c4ab6fa8929f57d4abfe52d5","source":{"kind":"arxiv","id":"2305.12683","version":1},"attestation_state":"computed","paper":{"title":"Mist: Towards Improved Adversarial Examples for Diffusion Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Chumeng Liang, Xiaoyu Wu","submitted_at":"2023-05-22T03:43:34Z","abstract_excerpt":"Diffusion Models (DMs) have empowered great success in artificial-intelligence-generated content, especially in artwork creation, yet raising new concerns in intellectual properties and copyright. For example, infringers can make profits by imitating non-authorized human-created paintings with DMs. Recent researches suggest that various adversarial examples for diffusion models can be effective tools against these copyright infringements. However, current adversarial examples show weakness in transferability over different painting-imitating methods and robustness under straightforward adversa"},"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":"2305.12683","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-05-22T03:43:34Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"91fe8f1375748b294623229ce5f7e74a6f31243ced3d09d218963f6de0a6336a","abstract_canon_sha256":"c4b1a954956d33e3c752c04cff5ad857a04f0e71dff6b50267d3f0832d0a2369"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:12:13.187112Z","signature_b64":"gdp7QVhyJMprFePBq2qRUhq0BNnXYBdjOHTnF631S1ov0g2sIhi5ZiSwqAqy3P7PIVWk+DlUqbQfqP4tGaRIDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cc23c11a94c872bcf9efa67a5ef37071065cf600c4ab6fa8929f57d4abfe52d5","last_reissued_at":"2026-07-05T06:12:13.186710Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:12:13.186710Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Mist: Towards Improved Adversarial Examples for Diffusion Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Chumeng Liang, Xiaoyu Wu","submitted_at":"2023-05-22T03:43:34Z","abstract_excerpt":"Diffusion Models (DMs) have empowered great success in artificial-intelligence-generated content, especially in artwork creation, yet raising new concerns in intellectual properties and copyright. For example, infringers can make profits by imitating non-authorized human-created paintings with DMs. Recent researches suggest that various adversarial examples for diffusion models can be effective tools against these copyright infringements. However, current adversarial examples show weakness in transferability over different painting-imitating methods and robustness under straightforward adversa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.12683","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/2305.12683/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":"2305.12683","created_at":"2026-07-05T06:12:13.186764+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.12683v1","created_at":"2026-07-05T06:12:13.186764+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.12683","created_at":"2026-07-05T06:12:13.186764+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZQR4CGUUZBZL","created_at":"2026-07-05T06:12:13.186764+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZQR4CGUUZBZLZ6PP","created_at":"2026-07-05T06:12:13.186764+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZQR4CGUU","created_at":"2026-07-05T06:12:13.186764+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.12263","citing_title":"VOID: Defeating Unauthorized Mimicry in Latent Diffusion Models","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2606.02453","citing_title":"Initialization is Half the Battle: Generating Diverse Images from a Guidance Potential Posterior","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2509.23279","citing_title":"Vid-Freeze: Protecting Images from Malicious Image-to-Video Generation via Temporal Freezing","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12919","citing_title":"GuardMarkGS: Unified Ownership Tracing and Edit Deterrence for 3D Gaussian Splatting","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23688","citing_title":"Do Protective Perturbations Really Protect Portrait Privacy under Real-world Image Transformations?","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2604.10837","citing_title":"Immune2V: Image Immunization Against Dual-Stream Image-to-Video Generation","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08405","citing_title":"SyncBreaker:Stage-Aware Multimodal Adversarial Attacks on Audio-Driven Talking Head Generation","ref_index":31,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZQR4CGUUZBZLZ6PPUZ5F543QOE","json":"https://pith.science/pith/ZQR4CGUUZBZLZ6PPUZ5F543QOE.json","graph_json":"https://pith.science/api/pith-number/ZQR4CGUUZBZLZ6PPUZ5F543QOE/graph.json","events_json":"https://pith.science/api/pith-number/ZQR4CGUUZBZLZ6PPUZ5F543QOE/events.json","paper":"https://pith.science/paper/ZQR4CGUU"},"agent_actions":{"view_html":"https://pith.science/pith/ZQR4CGUUZBZLZ6PPUZ5F543QOE","download_json":"https://pith.science/pith/ZQR4CGUUZBZLZ6PPUZ5F543QOE.json","view_paper":"https://pith.science/paper/ZQR4CGUU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.12683&json=true","fetch_graph":"https://pith.science/api/pith-number/ZQR4CGUUZBZLZ6PPUZ5F543QOE/graph.json","fetch_events":"https://pith.science/api/pith-number/ZQR4CGUUZBZLZ6PPUZ5F543QOE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZQR4CGUUZBZLZ6PPUZ5F543QOE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZQR4CGUUZBZLZ6PPUZ5F543QOE/action/storage_attestation","attest_author":"https://pith.science/pith/ZQR4CGUUZBZLZ6PPUZ5F543QOE/action/author_attestation","sign_citation":"https://pith.science/pith/ZQR4CGUUZBZLZ6PPUZ5F543QOE/action/citation_signature","submit_replication":"https://pith.science/pith/ZQR4CGUUZBZLZ6PPUZ5F543QOE/action/replication_record"}},"created_at":"2026-07-05T06:12:13.186764+00:00","updated_at":"2026-07-05T06:12:13.186764+00:00"}