{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:6ELPMYF57D527BFZP3YXY57U2S","short_pith_number":"pith:6ELPMYF5","canonical_record":{"source":{"id":"1705.07663","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2017-05-22T11:05:06Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"00881adcd2013d525a682e4c58e650cd2fe886bf8bd8137a3d0cfdc777420214","abstract_canon_sha256":"0418d8d66fb1080480e3a7ca733c252ab39ed4e6ee5c08c630b9443adcf87f98"},"schema_version":"1.0"},"canonical_sha256":"f116f660bdf8fbaf84b97ef17c77f4d4b093e39d896d6db460da33c3ea04fa68","source":{"kind":"arxiv","id":"1705.07663","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1705.07663","created_at":"2026-05-18T00:07:43Z"},{"alias_kind":"arxiv_version","alias_value":"1705.07663v4","created_at":"2026-05-18T00:07:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1705.07663","created_at":"2026-05-18T00:07:43Z"},{"alias_kind":"pith_short_12","alias_value":"6ELPMYF57D52","created_at":"2026-05-18T12:31:03Z"},{"alias_kind":"pith_short_16","alias_value":"6ELPMYF57D527BFZ","created_at":"2026-05-18T12:31:03Z"},{"alias_kind":"pith_short_8","alias_value":"6ELPMYF5","created_at":"2026-05-18T12:31:03Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:6ELPMYF57D527BFZP3YXY57U2S","target":"record","payload":{"canonical_record":{"source":{"id":"1705.07663","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2017-05-22T11:05:06Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"00881adcd2013d525a682e4c58e650cd2fe886bf8bd8137a3d0cfdc777420214","abstract_canon_sha256":"0418d8d66fb1080480e3a7ca733c252ab39ed4e6ee5c08c630b9443adcf87f98"},"schema_version":"1.0"},"canonical_sha256":"f116f660bdf8fbaf84b97ef17c77f4d4b093e39d896d6db460da33c3ea04fa68","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:07:43.849143Z","signature_b64":"86C95s2yE3UC99nYuDd8j9u2gHYikFXG2M1aGqI3bq15F+ivzDESsr2iPMADpwxKhaDxqR3qyNKj4ODz0gIkCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f116f660bdf8fbaf84b97ef17c77f4d4b093e39d896d6db460da33c3ea04fa68","last_reissued_at":"2026-05-18T00:07:43.848586Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:07:43.848586Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1705.07663","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:07:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2770XoCoxoJjgpvgBrSqm4sqFyuFXuVXXnvpbqxVuPruKvc6JrD+D0DcmyXRMB3ISbsQcELXIdlzfwCYTxTnDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-21T10:40:33.881671Z"},"content_sha256":"004506b8165063e2bb59cffeb23a113ce4939b91c567054c6bcc69df10184466","schema_version":"1.0","event_id":"sha256:004506b8165063e2bb59cffeb23a113ce4939b91c567054c6bcc69df10184466"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:6ELPMYF57D527BFZP3YXY57U2S","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"LOGAN: Membership Inference Attacks Against Generative Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CR","authors_text":"Emiliano De Cristofaro, George Danezis, Jamie Hayes, Luca Melis","submitted_at":"2017-05-22T11:05:06Z","abstract_excerpt":"Generative models estimate the underlying distribution of a dataset to generate realistic samples according to that distribution. In this paper, we present the first membership inference attacks against generative models: given a data point, the adversary determines whether or not it was used to train the model. Our attacks leverage Generative Adversarial Networks (GANs), which combine a discriminative and a generative model, to detect overfitting and recognize inputs that were part of training datasets, using the discriminator's capacity to learn statistical differences in distributions.\n  We"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1705.07663","kind":"arxiv","version":4},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:07:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VP8TofKz6klVAlvZjzUh9ENJJj8g6Cs+LstXH4q39WR6CsyTC4WSVGnKu9mNxaN0Eav2QIwLvih0AMkdDIsaAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-21T10:40:33.882025Z"},"content_sha256":"feab87fe2f49abe765b35d5cdd723d3747ebd6798b40d870d71e5375a7cae2e1","schema_version":"1.0","event_id":"sha256:feab87fe2f49abe765b35d5cdd723d3747ebd6798b40d870d71e5375a7cae2e1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6ELPMYF57D527BFZP3YXY57U2S/bundle.json","state_url":"https://pith.science/pith/6ELPMYF57D527BFZP3YXY57U2S/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6ELPMYF57D527BFZP3YXY57U2S/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-21T10:40:33Z","links":{"resolver":"https://pith.science/pith/6ELPMYF57D527BFZP3YXY57U2S","bundle":"https://pith.science/pith/6ELPMYF57D527BFZP3YXY57U2S/bundle.json","state":"https://pith.science/pith/6ELPMYF57D527BFZP3YXY57U2S/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6ELPMYF57D527BFZP3YXY57U2S/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:6ELPMYF57D527BFZP3YXY57U2S","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"0418d8d66fb1080480e3a7ca733c252ab39ed4e6ee5c08c630b9443adcf87f98","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2017-05-22T11:05:06Z","title_canon_sha256":"00881adcd2013d525a682e4c58e650cd2fe886bf8bd8137a3d0cfdc777420214"},"schema_version":"1.0","source":{"id":"1705.07663","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1705.07663","created_at":"2026-05-18T00:07:43Z"},{"alias_kind":"arxiv_version","alias_value":"1705.07663v4","created_at":"2026-05-18T00:07:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1705.07663","created_at":"2026-05-18T00:07:43Z"},{"alias_kind":"pith_short_12","alias_value":"6ELPMYF57D52","created_at":"2026-05-18T12:31:03Z"},{"alias_kind":"pith_short_16","alias_value":"6ELPMYF57D527BFZ","created_at":"2026-05-18T12:31:03Z"},{"alias_kind":"pith_short_8","alias_value":"6ELPMYF5","created_at":"2026-05-18T12:31:03Z"}],"graph_snapshots":[{"event_id":"sha256:feab87fe2f49abe765b35d5cdd723d3747ebd6798b40d870d71e5375a7cae2e1","target":"graph","created_at":"2026-05-18T00:07:43Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"Generative models estimate the underlying distribution of a dataset to generate realistic samples according to that distribution. In this paper, we present the first membership inference attacks against generative models: given a data point, the adversary determines whether or not it was used to train the model. Our attacks leverage Generative Adversarial Networks (GANs), which combine a discriminative and a generative model, to detect overfitting and recognize inputs that were part of training datasets, using the discriminator's capacity to learn statistical differences in distributions.\n  We","authors_text":"Emiliano De Cristofaro, George Danezis, Jamie Hayes, Luca Melis","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2017-05-22T11:05:06Z","title":"LOGAN: Membership Inference Attacks Against Generative Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1705.07663","kind":"arxiv","version":4},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:004506b8165063e2bb59cffeb23a113ce4939b91c567054c6bcc69df10184466","target":"record","created_at":"2026-05-18T00:07:43Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"0418d8d66fb1080480e3a7ca733c252ab39ed4e6ee5c08c630b9443adcf87f98","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2017-05-22T11:05:06Z","title_canon_sha256":"00881adcd2013d525a682e4c58e650cd2fe886bf8bd8137a3d0cfdc777420214"},"schema_version":"1.0","source":{"id":"1705.07663","kind":"arxiv","version":4}},"canonical_sha256":"f116f660bdf8fbaf84b97ef17c77f4d4b093e39d896d6db460da33c3ea04fa68","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f116f660bdf8fbaf84b97ef17c77f4d4b093e39d896d6db460da33c3ea04fa68","first_computed_at":"2026-05-18T00:07:43.848586Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:07:43.848586Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"86C95s2yE3UC99nYuDd8j9u2gHYikFXG2M1aGqI3bq15F+ivzDESsr2iPMADpwxKhaDxqR3qyNKj4ODz0gIkCA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:07:43.849143Z","signed_message":"canonical_sha256_bytes"},"source_id":"1705.07663","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:004506b8165063e2bb59cffeb23a113ce4939b91c567054c6bcc69df10184466","sha256:feab87fe2f49abe765b35d5cdd723d3747ebd6798b40d870d71e5375a7cae2e1"],"state_sha256":"23476b91ddd2ef0b73671913515eae05140812cb76eb74a7172521d3ee42f699"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"92Qjs1vkx9k0onGY2PntOjpDW46WvD17sROYDR+BzDUGytmN2ifUl+drYyX4lUj+AMz8zFkynOU4y29bkerfBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-21T10:40:33.884152Z","bundle_sha256":"823ce88d82c1e80ea7ad47e3b4aa556b1d6cf5df58711186771426ac3c334ab1"}}