{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:C52WKFGSNMTWRMSGYEQSO6DR7H","short_pith_number":"pith:C52WKFGS","schema_version":"1.0","canonical_sha256":"17756514d26b2768b246c121277871f9cfdade9a0853f1e22673fedac25ad037","source":{"kind":"arxiv","id":"2302.09923","version":2},"attestation_state":"computed","paper":{"title":"Prompt Stealing Attacks Against Text-to-Image Generation Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CR","authors_text":"Michael Backes, Xinyue Shen, Yang Zhang, Yiting Qu","submitted_at":"2023-02-20T11:37:28Z","abstract_excerpt":"Text-to-Image generation models have revolutionized the artwork design process and enabled anyone to create high-quality images by entering text descriptions called prompts. Creating a high-quality prompt that consists of a subject and several modifiers can be time-consuming and costly. In consequence, a trend of trading high-quality prompts on specialized marketplaces has emerged. In this paper, we perform the first study on understanding the threat of a novel attack, namely prompt stealing attack, which aims to steal prompts from generated images by text-to-image generation models. Successfu"},"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":"2302.09923","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2023-02-20T11:37:28Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"affa1d264208a6addde7144f020f73b25d9cc34807a048af08d1d098df7063e3","abstract_canon_sha256":"37b4393921d8d9f4ab2f760f42dd679611cf1f9865b9ad7ddf943766f2e75731"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:07:55.611959Z","signature_b64":"dzZfv7TNShZZigkY2EzDMB0QKqwUwOdu96m63ObR2AMzJmpvf5KCXxr8GiaUpCZLSA1jotRQHuIJzDgZ1eBCDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"17756514d26b2768b246c121277871f9cfdade9a0853f1e22673fedac25ad037","last_reissued_at":"2026-07-05T08:07:55.611440Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:07:55.611440Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Prompt Stealing Attacks Against Text-to-Image Generation Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CR","authors_text":"Michael Backes, Xinyue Shen, Yang Zhang, Yiting Qu","submitted_at":"2023-02-20T11:37:28Z","abstract_excerpt":"Text-to-Image generation models have revolutionized the artwork design process and enabled anyone to create high-quality images by entering text descriptions called prompts. Creating a high-quality prompt that consists of a subject and several modifiers can be time-consuming and costly. In consequence, a trend of trading high-quality prompts on specialized marketplaces has emerged. In this paper, we perform the first study on understanding the threat of a novel attack, namely prompt stealing attack, which aims to steal prompts from generated images by text-to-image generation models. Successfu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.09923","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/2302.09923/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":"2302.09923","created_at":"2026-07-05T08:07:55.611540+00:00"},{"alias_kind":"arxiv_version","alias_value":"2302.09923v2","created_at":"2026-07-05T08:07:55.611540+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.09923","created_at":"2026-07-05T08:07:55.611540+00:00"},{"alias_kind":"pith_short_12","alias_value":"C52WKFGSNMTW","created_at":"2026-07-05T08:07:55.611540+00:00"},{"alias_kind":"pith_short_16","alias_value":"C52WKFGSNMTWRMSG","created_at":"2026-07-05T08:07:55.611540+00:00"},{"alias_kind":"pith_short_8","alias_value":"C52WKFGS","created_at":"2026-07-05T08:07:55.611540+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.09861","citing_title":"Evolutionary Token-Level Prompt Optimization for Diffusion Models","ref_index":9,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/C52WKFGSNMTWRMSGYEQSO6DR7H","json":"https://pith.science/pith/C52WKFGSNMTWRMSGYEQSO6DR7H.json","graph_json":"https://pith.science/api/pith-number/C52WKFGSNMTWRMSGYEQSO6DR7H/graph.json","events_json":"https://pith.science/api/pith-number/C52WKFGSNMTWRMSGYEQSO6DR7H/events.json","paper":"https://pith.science/paper/C52WKFGS"},"agent_actions":{"view_html":"https://pith.science/pith/C52WKFGSNMTWRMSGYEQSO6DR7H","download_json":"https://pith.science/pith/C52WKFGSNMTWRMSGYEQSO6DR7H.json","view_paper":"https://pith.science/paper/C52WKFGS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2302.09923&json=true","fetch_graph":"https://pith.science/api/pith-number/C52WKFGSNMTWRMSGYEQSO6DR7H/graph.json","fetch_events":"https://pith.science/api/pith-number/C52WKFGSNMTWRMSGYEQSO6DR7H/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/C52WKFGSNMTWRMSGYEQSO6DR7H/action/timestamp_anchor","attest_storage":"https://pith.science/pith/C52WKFGSNMTWRMSGYEQSO6DR7H/action/storage_attestation","attest_author":"https://pith.science/pith/C52WKFGSNMTWRMSGYEQSO6DR7H/action/author_attestation","sign_citation":"https://pith.science/pith/C52WKFGSNMTWRMSGYEQSO6DR7H/action/citation_signature","submit_replication":"https://pith.science/pith/C52WKFGSNMTWRMSGYEQSO6DR7H/action/replication_record"}},"created_at":"2026-07-05T08:07:55.611540+00:00","updated_at":"2026-07-05T08:07:55.611540+00:00"}