{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:K5PH4GRU7WJSZDIZEE2C6GBMXD","short_pith_number":"pith:K5PH4GRU","schema_version":"1.0","canonical_sha256":"575e7e1a34fd932c8d1921342f182cb8d6ca85e3faac7f21d798ac76c21e3e52","source":{"kind":"arxiv","id":"2201.03139","version":2},"attestation_state":"computed","paper":{"title":"Differentially Private Generative Adversarial Networks with Model Inversion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR"],"primary_cat":"cs.LG","authors_text":"Chen-Nee Chuah, Dongjie Chen, Sally Ozonoff, Sen-Ching Samson Cheung","submitted_at":"2022-01-10T02:26:26Z","abstract_excerpt":"To protect sensitive data in training a Generative Adversarial Network (GAN), the standard approach is to use differentially private (DP) stochastic gradient descent method in which controlled noise is added to the gradients. The quality of the output synthetic samples can be adversely affected and the training of the network may not even converge in the presence of these noises. We propose Differentially Private Model Inversion (DPMI) method where the private data is first mapped to the latent space via a public generator, followed by a lower-dimensional DP-GAN with better convergent properti"},"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":"2201.03139","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-01-10T02:26:26Z","cross_cats_sorted":["cs.CR"],"title_canon_sha256":"8f2796560d52c79326f29bcee4fe80df396f4e6700f85fcd89001d7904ea949e","abstract_canon_sha256":"1455020c2731bf25920750ea4b3a975ae967baba02f178603059f5d9e05fb73b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:10:53.856015Z","signature_b64":"+5/kvV8sazIE4vfrlVYwAFXxDNjSe+JCv3Hc+isP2H8h9Fqk5+Mj5wLvtUmzbC7IUmxWzGPrRsq+p2/VpfTcCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"575e7e1a34fd932c8d1921342f182cb8d6ca85e3faac7f21d798ac76c21e3e52","last_reissued_at":"2026-07-05T05:10:53.855609Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:10:53.855609Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Differentially Private Generative Adversarial Networks with Model Inversion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR"],"primary_cat":"cs.LG","authors_text":"Chen-Nee Chuah, Dongjie Chen, Sally Ozonoff, Sen-Ching Samson Cheung","submitted_at":"2022-01-10T02:26:26Z","abstract_excerpt":"To protect sensitive data in training a Generative Adversarial Network (GAN), the standard approach is to use differentially private (DP) stochastic gradient descent method in which controlled noise is added to the gradients. The quality of the output synthetic samples can be adversely affected and the training of the network may not even converge in the presence of these noises. We propose Differentially Private Model Inversion (DPMI) method where the private data is first mapped to the latent space via a public generator, followed by a lower-dimensional DP-GAN with better convergent properti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.03139","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/2201.03139/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":"2201.03139","created_at":"2026-07-05T05:10:53.855679+00:00"},{"alias_kind":"arxiv_version","alias_value":"2201.03139v2","created_at":"2026-07-05T05:10:53.855679+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.03139","created_at":"2026-07-05T05:10:53.855679+00:00"},{"alias_kind":"pith_short_12","alias_value":"K5PH4GRU7WJS","created_at":"2026-07-05T05:10:53.855679+00:00"},{"alias_kind":"pith_short_16","alias_value":"K5PH4GRU7WJSZDIZ","created_at":"2026-07-05T05:10:53.855679+00:00"},{"alias_kind":"pith_short_8","alias_value":"K5PH4GRU","created_at":"2026-07-05T05:10:53.855679+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/K5PH4GRU7WJSZDIZEE2C6GBMXD","json":"https://pith.science/pith/K5PH4GRU7WJSZDIZEE2C6GBMXD.json","graph_json":"https://pith.science/api/pith-number/K5PH4GRU7WJSZDIZEE2C6GBMXD/graph.json","events_json":"https://pith.science/api/pith-number/K5PH4GRU7WJSZDIZEE2C6GBMXD/events.json","paper":"https://pith.science/paper/K5PH4GRU"},"agent_actions":{"view_html":"https://pith.science/pith/K5PH4GRU7WJSZDIZEE2C6GBMXD","download_json":"https://pith.science/pith/K5PH4GRU7WJSZDIZEE2C6GBMXD.json","view_paper":"https://pith.science/paper/K5PH4GRU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2201.03139&json=true","fetch_graph":"https://pith.science/api/pith-number/K5PH4GRU7WJSZDIZEE2C6GBMXD/graph.json","fetch_events":"https://pith.science/api/pith-number/K5PH4GRU7WJSZDIZEE2C6GBMXD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/K5PH4GRU7WJSZDIZEE2C6GBMXD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/K5PH4GRU7WJSZDIZEE2C6GBMXD/action/storage_attestation","attest_author":"https://pith.science/pith/K5PH4GRU7WJSZDIZEE2C6GBMXD/action/author_attestation","sign_citation":"https://pith.science/pith/K5PH4GRU7WJSZDIZEE2C6GBMXD/action/citation_signature","submit_replication":"https://pith.science/pith/K5PH4GRU7WJSZDIZEE2C6GBMXD/action/replication_record"}},"created_at":"2026-07-05T05:10:53.855679+00:00","updated_at":"2026-07-05T05:10:53.855679+00:00"}