{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:VI7GX247TT4JJHFDD33LDXZVID","short_pith_number":"pith:VI7GX247","schema_version":"1.0","canonical_sha256":"aa3e6beb9f9cf8949ca31ef6b1df3540dd5c030311454a54b1e68e93ef680d4d","source":{"kind":"arxiv","id":"2305.13873","version":2},"attestation_state":"computed","paper":{"title":"Unsafe Diffusion: On the Generation of Unsafe Images and Hateful Memes From Text-To-Image Models","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.CR","cs.CY","cs.LG","cs.SI"],"primary_cat":"cs.CV","authors_text":"Michael Backes, Savvas Zannettou, Xinlei He, Xinyue Shen, Yang Zhang, Yiting Qu","submitted_at":"2023-05-23T09:48:16Z","abstract_excerpt":"State-of-the-art Text-to-Image models like Stable Diffusion and DALLE$\\cdot$2 are revolutionizing how people generate visual content. At the same time, society has serious concerns about how adversaries can exploit such models to generate unsafe images. In this work, we focus on demystifying the generation of unsafe images and hateful memes from Text-to-Image models. We first construct a typology of unsafe images consisting of five categories (sexually explicit, violent, disturbing, hateful, and political). Then, we assess the proportion of unsafe images generated by four advanced Text-to-Imag"},"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":"2305.13873","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2023-05-23T09:48:16Z","cross_cats_sorted":["cs.CR","cs.CY","cs.LG","cs.SI"],"title_canon_sha256":"0a79249d0be1527a113b1fa7182914c61496719d7b49d525eb774ded5033a076","abstract_canon_sha256":"32ddfa0ba8b1f330cd9a4e7e4861f4fcd16f7931948e87f80e426c448c0f55b7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:41:49.598564Z","signature_b64":"KbaUQdaIO/krov3GrzQjxLutfyTsXbV3UoKRrMMtZOjASOv+J/ZhC3OwHOMkrM5NZA7tPz+1mNbQCDQ+Dy29Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"aa3e6beb9f9cf8949ca31ef6b1df3540dd5c030311454a54b1e68e93ef680d4d","last_reissued_at":"2026-07-05T06:41:49.598043Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:41:49.598043Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Unsafe Diffusion: On the Generation of Unsafe Images and Hateful Memes From Text-To-Image Models","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.CR","cs.CY","cs.LG","cs.SI"],"primary_cat":"cs.CV","authors_text":"Michael Backes, Savvas Zannettou, Xinlei He, Xinyue Shen, Yang Zhang, Yiting Qu","submitted_at":"2023-05-23T09:48:16Z","abstract_excerpt":"State-of-the-art Text-to-Image models like Stable Diffusion and DALLE$\\cdot$2 are revolutionizing how people generate visual content. At the same time, society has serious concerns about how adversaries can exploit such models to generate unsafe images. In this work, we focus on demystifying the generation of unsafe images and hateful memes from Text-to-Image models. We first construct a typology of unsafe images consisting of five categories (sexually explicit, violent, disturbing, hateful, and political). Then, we assess the proportion of unsafe images generated by four advanced Text-to-Imag"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.13873","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/2305.13873/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":"2305.13873","created_at":"2026-07-05T06:41:49.598103+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.13873v2","created_at":"2026-07-05T06:41:49.598103+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.13873","created_at":"2026-07-05T06:41:49.598103+00:00"},{"alias_kind":"pith_short_12","alias_value":"VI7GX247TT4J","created_at":"2026-07-05T06:41:49.598103+00:00"},{"alias_kind":"pith_short_16","alias_value":"VI7GX247TT4JJHFD","created_at":"2026-07-05T06:41:49.598103+00:00"},{"alias_kind":"pith_short_8","alias_value":"VI7GX247","created_at":"2026-07-05T06:41:49.598103+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.01272","citing_title":"PromptSafe: Gated Prompt Tuning for Safe Text-to-Image Generation","ref_index":36,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VI7GX247TT4JJHFDD33LDXZVID","json":"https://pith.science/pith/VI7GX247TT4JJHFDD33LDXZVID.json","graph_json":"https://pith.science/api/pith-number/VI7GX247TT4JJHFDD33LDXZVID/graph.json","events_json":"https://pith.science/api/pith-number/VI7GX247TT4JJHFDD33LDXZVID/events.json","paper":"https://pith.science/paper/VI7GX247"},"agent_actions":{"view_html":"https://pith.science/pith/VI7GX247TT4JJHFDD33LDXZVID","download_json":"https://pith.science/pith/VI7GX247TT4JJHFDD33LDXZVID.json","view_paper":"https://pith.science/paper/VI7GX247","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.13873&json=true","fetch_graph":"https://pith.science/api/pith-number/VI7GX247TT4JJHFDD33LDXZVID/graph.json","fetch_events":"https://pith.science/api/pith-number/VI7GX247TT4JJHFDD33LDXZVID/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VI7GX247TT4JJHFDD33LDXZVID/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VI7GX247TT4JJHFDD33LDXZVID/action/storage_attestation","attest_author":"https://pith.science/pith/VI7GX247TT4JJHFDD33LDXZVID/action/author_attestation","sign_citation":"https://pith.science/pith/VI7GX247TT4JJHFDD33LDXZVID/action/citation_signature","submit_replication":"https://pith.science/pith/VI7GX247TT4JJHFDD33LDXZVID/action/replication_record"}},"created_at":"2026-07-05T06:41:49.598103+00:00","updated_at":"2026-07-05T06:41:49.598103+00:00"}