{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:KPWDJ2GNT5AYCLDAIS4UWKVTGS","short_pith_number":"pith:KPWDJ2GN","schema_version":"1.0","canonical_sha256":"53ec34e8cd9f41812c6044b94b2ab334baf00add85829312c876e19e32dd3209","source":{"kind":"arxiv","id":"2306.01322","version":1},"attestation_state":"computed","paper":{"title":"Privacy Distillation: Reducing Re-identification Risk of Multimodal Diffusion Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CR","cs.CV"],"primary_cat":"cs.LG","authors_text":"Grzegorz Jacenk\\'ow, Jorge Cardoso, Pedro Sanchez, Sotirios A. Tsaftaris, Virginia Fernandez, Walter Hugo Lopez Pinaya","submitted_at":"2023-06-02T07:44:00Z","abstract_excerpt":"Knowledge distillation in neural networks refers to compressing a large model or dataset into a smaller version of itself. We introduce Privacy Distillation, a framework that allows a text-to-image generative model to teach another model without exposing it to identifiable data. Here, we are interested in the privacy issue faced by a data provider who wishes to share their data via a multimodal generative model. A question that immediately arises is ``How can a data provider ensure that the generative model is not leaking identifiable information about a patient?''. Our solution consists of (1"},"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":"2306.01322","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-06-02T07:44:00Z","cross_cats_sorted":["cs.CR","cs.CV"],"title_canon_sha256":"b46429b1a9594d319039147610cd23e8d07aac876e32930b5fe05b7cdd4548cd","abstract_canon_sha256":"0a8e37bfaac5069be3273cbf10e213441a1c1439e12baf5ec2093f8a53c45441"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:16:52.533797Z","signature_b64":"hVz8ftD+/frY8vdtXH7d5XywRPB2xum9LGgTAC5PCXt1bStwod0TLGWkdLAIl8Lx0qvP1qRPfOtub7ZpMKMgAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"53ec34e8cd9f41812c6044b94b2ab334baf00add85829312c876e19e32dd3209","last_reissued_at":"2026-07-05T06:16:52.533394Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:16:52.533394Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Privacy Distillation: Reducing Re-identification Risk of Multimodal Diffusion Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CR","cs.CV"],"primary_cat":"cs.LG","authors_text":"Grzegorz Jacenk\\'ow, Jorge Cardoso, Pedro Sanchez, Sotirios A. Tsaftaris, Virginia Fernandez, Walter Hugo Lopez Pinaya","submitted_at":"2023-06-02T07:44:00Z","abstract_excerpt":"Knowledge distillation in neural networks refers to compressing a large model or dataset into a smaller version of itself. We introduce Privacy Distillation, a framework that allows a text-to-image generative model to teach another model without exposing it to identifiable data. Here, we are interested in the privacy issue faced by a data provider who wishes to share their data via a multimodal generative model. A question that immediately arises is ``How can a data provider ensure that the generative model is not leaking identifiable information about a patient?''. Our solution consists of (1"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.01322","kind":"arxiv","version":1},"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/2306.01322/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":"2306.01322","created_at":"2026-07-05T06:16:52.533450+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.01322v1","created_at":"2026-07-05T06:16:52.533450+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.01322","created_at":"2026-07-05T06:16:52.533450+00:00"},{"alias_kind":"pith_short_12","alias_value":"KPWDJ2GNT5AY","created_at":"2026-07-05T06:16:52.533450+00:00"},{"alias_kind":"pith_short_16","alias_value":"KPWDJ2GNT5AYCLDA","created_at":"2026-07-05T06:16:52.533450+00:00"},{"alias_kind":"pith_short_8","alias_value":"KPWDJ2GN","created_at":"2026-07-05T06:16:52.533450+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/KPWDJ2GNT5AYCLDAIS4UWKVTGS","json":"https://pith.science/pith/KPWDJ2GNT5AYCLDAIS4UWKVTGS.json","graph_json":"https://pith.science/api/pith-number/KPWDJ2GNT5AYCLDAIS4UWKVTGS/graph.json","events_json":"https://pith.science/api/pith-number/KPWDJ2GNT5AYCLDAIS4UWKVTGS/events.json","paper":"https://pith.science/paper/KPWDJ2GN"},"agent_actions":{"view_html":"https://pith.science/pith/KPWDJ2GNT5AYCLDAIS4UWKVTGS","download_json":"https://pith.science/pith/KPWDJ2GNT5AYCLDAIS4UWKVTGS.json","view_paper":"https://pith.science/paper/KPWDJ2GN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.01322&json=true","fetch_graph":"https://pith.science/api/pith-number/KPWDJ2GNT5AYCLDAIS4UWKVTGS/graph.json","fetch_events":"https://pith.science/api/pith-number/KPWDJ2GNT5AYCLDAIS4UWKVTGS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KPWDJ2GNT5AYCLDAIS4UWKVTGS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KPWDJ2GNT5AYCLDAIS4UWKVTGS/action/storage_attestation","attest_author":"https://pith.science/pith/KPWDJ2GNT5AYCLDAIS4UWKVTGS/action/author_attestation","sign_citation":"https://pith.science/pith/KPWDJ2GNT5AYCLDAIS4UWKVTGS/action/citation_signature","submit_replication":"https://pith.science/pith/KPWDJ2GNT5AYCLDAIS4UWKVTGS/action/replication_record"}},"created_at":"2026-07-05T06:16:52.533450+00:00","updated_at":"2026-07-05T06:16:52.533450+00:00"}