{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:CQMTAURPSJ2Y7UKVLI27YRSB5R","short_pith_number":"pith:CQMTAURP","schema_version":"1.0","canonical_sha256":"141930522f92758fd1555a35fc4641ec665e5e1b3bac687136c33990854b39f7","source":{"kind":"arxiv","id":"2307.12872","version":2},"attestation_state":"computed","paper":{"title":"Latent Code Augmentation Based on Stable Diffusion for Data-free Substitute Attacks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR","cs.LG"],"primary_cat":"cs.CV","authors_text":"Lingzhuang Meng, Lixu Zhang, Mingwen Shao, Wangmeng Zuo, Yuanjian Qiao","submitted_at":"2023-07-24T15:10:22Z","abstract_excerpt":"Since the training data of the target model is not available in the black-box substitute attack, most recent schemes utilize GANs to generate data for training the substitute model. However, these GANs-based schemes suffer from low training efficiency as the generator needs to be retrained for each target model during the substitute training process, as well as low generation quality. To overcome these limitations, we consider utilizing the diffusion model to generate data, and propose a novel data-free substitute attack scheme based on the Stable Diffusion (SD) to improve the efficiency and a"},"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":"2307.12872","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-07-24T15:10:22Z","cross_cats_sorted":["cs.CR","cs.LG"],"title_canon_sha256":"97d3415f86f3a609f923481d8aa1aab7ba39cf9f363729a777da2884f85662ad","abstract_canon_sha256":"20181b0370e4db07cfb71d1f0409314c084ebb79139a19ae18d350ba36f11277"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:25:31.554432Z","signature_b64":"6hjNxDj1RmH4P5DUllrvsiZaXBBdnfoztmpO9aBnj0W37jDUbvj99piHRIsF5cS9SFIffAv2xT4OrwrnxnzJDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"141930522f92758fd1555a35fc4641ec665e5e1b3bac687136c33990854b39f7","last_reissued_at":"2026-07-05T09:25:31.554051Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:25:31.554051Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Latent Code Augmentation Based on Stable Diffusion for Data-free Substitute Attacks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR","cs.LG"],"primary_cat":"cs.CV","authors_text":"Lingzhuang Meng, Lixu Zhang, Mingwen Shao, Wangmeng Zuo, Yuanjian Qiao","submitted_at":"2023-07-24T15:10:22Z","abstract_excerpt":"Since the training data of the target model is not available in the black-box substitute attack, most recent schemes utilize GANs to generate data for training the substitute model. However, these GANs-based schemes suffer from low training efficiency as the generator needs to be retrained for each target model during the substitute training process, as well as low generation quality. To overcome these limitations, we consider utilizing the diffusion model to generate data, and propose a novel data-free substitute attack scheme based on the Stable Diffusion (SD) to improve the efficiency and a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.12872","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/2307.12872/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":"2307.12872","created_at":"2026-07-05T09:25:31.554106+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.12872v2","created_at":"2026-07-05T09:25:31.554106+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.12872","created_at":"2026-07-05T09:25:31.554106+00:00"},{"alias_kind":"pith_short_12","alias_value":"CQMTAURPSJ2Y","created_at":"2026-07-05T09:25:31.554106+00:00"},{"alias_kind":"pith_short_16","alias_value":"CQMTAURPSJ2Y7UKV","created_at":"2026-07-05T09:25:31.554106+00:00"},{"alias_kind":"pith_short_8","alias_value":"CQMTAURP","created_at":"2026-07-05T09:25:31.554106+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.16969","citing_title":"LLM4MEA: Data-free Model Extraction Attacks on Sequential Recommenders via Large Language Models","ref_index":24,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CQMTAURPSJ2Y7UKVLI27YRSB5R","json":"https://pith.science/pith/CQMTAURPSJ2Y7UKVLI27YRSB5R.json","graph_json":"https://pith.science/api/pith-number/CQMTAURPSJ2Y7UKVLI27YRSB5R/graph.json","events_json":"https://pith.science/api/pith-number/CQMTAURPSJ2Y7UKVLI27YRSB5R/events.json","paper":"https://pith.science/paper/CQMTAURP"},"agent_actions":{"view_html":"https://pith.science/pith/CQMTAURPSJ2Y7UKVLI27YRSB5R","download_json":"https://pith.science/pith/CQMTAURPSJ2Y7UKVLI27YRSB5R.json","view_paper":"https://pith.science/paper/CQMTAURP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.12872&json=true","fetch_graph":"https://pith.science/api/pith-number/CQMTAURPSJ2Y7UKVLI27YRSB5R/graph.json","fetch_events":"https://pith.science/api/pith-number/CQMTAURPSJ2Y7UKVLI27YRSB5R/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CQMTAURPSJ2Y7UKVLI27YRSB5R/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CQMTAURPSJ2Y7UKVLI27YRSB5R/action/storage_attestation","attest_author":"https://pith.science/pith/CQMTAURPSJ2Y7UKVLI27YRSB5R/action/author_attestation","sign_citation":"https://pith.science/pith/CQMTAURPSJ2Y7UKVLI27YRSB5R/action/citation_signature","submit_replication":"https://pith.science/pith/CQMTAURPSJ2Y7UKVLI27YRSB5R/action/replication_record"}},"created_at":"2026-07-05T09:25:31.554106+00:00","updated_at":"2026-07-05T09:25:31.554106+00:00"}