{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:ID34CTPACFSKJJTX3Q3TOOZ4TI","short_pith_number":"pith:ID34CTPA","schema_version":"1.0","canonical_sha256":"40f7c14de01164a4a677dc37373b3c9a34650f7a18258ddd135cbe3c65a8dd01","source":{"kind":"arxiv","id":"1908.07882","version":3},"attestation_state":"computed","paper":{"title":"Generalization in Generative Adversarial Networks: A Novel Perspective from Privacy Protection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR","stat.ML"],"primary_cat":"cs.LG","authors_text":"Bingzhe Wu, Chaochao Chen, Guangyu Sun, Haoyang Xu, Jun Zhou, Li Wang, Shiwan Zhao, Xiaolu Zhang","submitted_at":"2019-08-21T14:09:32Z","abstract_excerpt":"In this paper, we aim to understand the generalization properties of generative adversarial networks (GANs) from a new perspective of privacy protection. Theoretically, we prove that a differentially private learning algorithm used for training the GAN does not overfit to a certain degree, i.e., the generalization gap can be bounded. Moreover, some recent works, such as the Bayesian GAN, can be re-interpreted based on our theoretical insight from privacy protection. Quantitatively, to evaluate the information leakage of well-trained GAN models, we perform various membership attacks on these mo"},"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":"1908.07882","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-08-21T14:09:32Z","cross_cats_sorted":["cs.CR","stat.ML"],"title_canon_sha256":"01699855593df34ebc5eab96c328de6bb1d8556244f8f4de1a18f00f5b6a2c51","abstract_canon_sha256":"97bbdaf90095d76e332f75cf447ec9f67f05771b5e7b99238f0887b4c07c77ee"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:07:07.850645Z","signature_b64":"T0lNDtGzy2APvF0Ue+PcsRgJff6uJ6+d3IBFHZQ01wMVU8IeecFi3IReZiXhz8DCKlldnbL4gHGrfVh+Qv2gBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"40f7c14de01164a4a677dc37373b3c9a34650f7a18258ddd135cbe3c65a8dd01","last_reissued_at":"2026-07-05T00:07:07.850191Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:07:07.850191Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Generalization in Generative Adversarial Networks: A Novel Perspective from Privacy Protection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR","stat.ML"],"primary_cat":"cs.LG","authors_text":"Bingzhe Wu, Chaochao Chen, Guangyu Sun, Haoyang Xu, Jun Zhou, Li Wang, Shiwan Zhao, Xiaolu Zhang","submitted_at":"2019-08-21T14:09:32Z","abstract_excerpt":"In this paper, we aim to understand the generalization properties of generative adversarial networks (GANs) from a new perspective of privacy protection. Theoretically, we prove that a differentially private learning algorithm used for training the GAN does not overfit to a certain degree, i.e., the generalization gap can be bounded. Moreover, some recent works, such as the Bayesian GAN, can be re-interpreted based on our theoretical insight from privacy protection. Quantitatively, to evaluate the information leakage of well-trained GAN models, we perform various membership attacks on these mo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.07882","kind":"arxiv","version":3},"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/1908.07882/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":"1908.07882","created_at":"2026-07-05T00:07:07.850252+00:00"},{"alias_kind":"arxiv_version","alias_value":"1908.07882v3","created_at":"2026-07-05T00:07:07.850252+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.07882","created_at":"2026-07-05T00:07:07.850252+00:00"},{"alias_kind":"pith_short_12","alias_value":"ID34CTPACFSK","created_at":"2026-07-05T00:07:07.850252+00:00"},{"alias_kind":"pith_short_16","alias_value":"ID34CTPACFSKJJTX","created_at":"2026-07-05T00:07:07.850252+00:00"},{"alias_kind":"pith_short_8","alias_value":"ID34CTPA","created_at":"2026-07-05T00:07:07.850252+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/ID34CTPACFSKJJTX3Q3TOOZ4TI","json":"https://pith.science/pith/ID34CTPACFSKJJTX3Q3TOOZ4TI.json","graph_json":"https://pith.science/api/pith-number/ID34CTPACFSKJJTX3Q3TOOZ4TI/graph.json","events_json":"https://pith.science/api/pith-number/ID34CTPACFSKJJTX3Q3TOOZ4TI/events.json","paper":"https://pith.science/paper/ID34CTPA"},"agent_actions":{"view_html":"https://pith.science/pith/ID34CTPACFSKJJTX3Q3TOOZ4TI","download_json":"https://pith.science/pith/ID34CTPACFSKJJTX3Q3TOOZ4TI.json","view_paper":"https://pith.science/paper/ID34CTPA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1908.07882&json=true","fetch_graph":"https://pith.science/api/pith-number/ID34CTPACFSKJJTX3Q3TOOZ4TI/graph.json","fetch_events":"https://pith.science/api/pith-number/ID34CTPACFSKJJTX3Q3TOOZ4TI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ID34CTPACFSKJJTX3Q3TOOZ4TI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ID34CTPACFSKJJTX3Q3TOOZ4TI/action/storage_attestation","attest_author":"https://pith.science/pith/ID34CTPACFSKJJTX3Q3TOOZ4TI/action/author_attestation","sign_citation":"https://pith.science/pith/ID34CTPACFSKJJTX3Q3TOOZ4TI/action/citation_signature","submit_replication":"https://pith.science/pith/ID34CTPACFSKJJTX3Q3TOOZ4TI/action/replication_record"}},"created_at":"2026-07-05T00:07:07.850252+00:00","updated_at":"2026-07-05T00:07:07.850252+00:00"}