{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:E2UFGDHL2NTBSK4JBPAIXO2FD2","short_pith_number":"pith:E2UFGDHL","schema_version":"1.0","canonical_sha256":"26a8530cebd366192b890bc08bbb451ea05f466926ee2ac621952fabe4210fdf","source":{"kind":"arxiv","id":"2309.13002","version":2},"attestation_state":"computed","paper":{"title":"Expressive variational quantum circuits provide inherent privacy in federated learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR","cs.LG"],"primary_cat":"quant-ph","authors_text":"Changhao Li, Jamie Heredge, Marco Pistoia, Niraj Kumar, Shaltiel Eloul, Shree Hari Sureshbabu","submitted_at":"2023-09-22T17:04:50Z","abstract_excerpt":"Federated learning has emerged as a viable distributed solution to train machine learning models without the actual need to share data with the central aggregator. However, standard neural network-based federated learning models have been shown to be susceptible to data leakage from the gradients shared with the server. In this work, we introduce federated learning with variational quantum circuit model built using expressive encoding maps coupled with overparameterized ans\\\"atze. We show that expressive maps lead to inherent privacy against gradient inversion attacks, while overparameterizati"},"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":"2309.13002","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"quant-ph","submitted_at":"2023-09-22T17:04:50Z","cross_cats_sorted":["cs.CR","cs.LG"],"title_canon_sha256":"e819019c1435300387bfe05faa305c05b1f4b3df68e4b0aed502371f6bd206ff","abstract_canon_sha256":"cd16b282a1d750813b44da257b9dc1abb4a4706d1e331c79fff3475ef8f01b7d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:53:46.040736Z","signature_b64":"r9gJP9EbDAUfBlH5R0AkTDsVYIPAPwSyE+Hb0Se9dyJGz/4VpmdbvQ+C2dUd5ZYDSFH/1dO5d1M23vRE5fgFDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"26a8530cebd366192b890bc08bbb451ea05f466926ee2ac621952fabe4210fdf","last_reissued_at":"2026-07-05T06:53:46.040197Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:53:46.040197Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Expressive variational quantum circuits provide inherent privacy in federated learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR","cs.LG"],"primary_cat":"quant-ph","authors_text":"Changhao Li, Jamie Heredge, Marco Pistoia, Niraj Kumar, Shaltiel Eloul, Shree Hari Sureshbabu","submitted_at":"2023-09-22T17:04:50Z","abstract_excerpt":"Federated learning has emerged as a viable distributed solution to train machine learning models without the actual need to share data with the central aggregator. However, standard neural network-based federated learning models have been shown to be susceptible to data leakage from the gradients shared with the server. In this work, we introduce federated learning with variational quantum circuit model built using expressive encoding maps coupled with overparameterized ans\\\"atze. We show that expressive maps lead to inherent privacy against gradient inversion attacks, while overparameterizati"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.13002","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/2309.13002/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":"2309.13002","created_at":"2026-07-05T06:53:46.040259+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.13002v2","created_at":"2026-07-05T06:53:46.040259+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.13002","created_at":"2026-07-05T06:53:46.040259+00:00"},{"alias_kind":"pith_short_12","alias_value":"E2UFGDHL2NTB","created_at":"2026-07-05T06:53:46.040259+00:00"},{"alias_kind":"pith_short_16","alias_value":"E2UFGDHL2NTBSK4J","created_at":"2026-07-05T06:53:46.040259+00:00"},{"alias_kind":"pith_short_8","alias_value":"E2UFGDHL","created_at":"2026-07-05T06:53:46.040259+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2504.12806","citing_title":"A Numerical Gradient Inversion Attack in Variational Quantum Neural-Networks","ref_index":27,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/E2UFGDHL2NTBSK4JBPAIXO2FD2","json":"https://pith.science/pith/E2UFGDHL2NTBSK4JBPAIXO2FD2.json","graph_json":"https://pith.science/api/pith-number/E2UFGDHL2NTBSK4JBPAIXO2FD2/graph.json","events_json":"https://pith.science/api/pith-number/E2UFGDHL2NTBSK4JBPAIXO2FD2/events.json","paper":"https://pith.science/paper/E2UFGDHL"},"agent_actions":{"view_html":"https://pith.science/pith/E2UFGDHL2NTBSK4JBPAIXO2FD2","download_json":"https://pith.science/pith/E2UFGDHL2NTBSK4JBPAIXO2FD2.json","view_paper":"https://pith.science/paper/E2UFGDHL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.13002&json=true","fetch_graph":"https://pith.science/api/pith-number/E2UFGDHL2NTBSK4JBPAIXO2FD2/graph.json","fetch_events":"https://pith.science/api/pith-number/E2UFGDHL2NTBSK4JBPAIXO2FD2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/E2UFGDHL2NTBSK4JBPAIXO2FD2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/E2UFGDHL2NTBSK4JBPAIXO2FD2/action/storage_attestation","attest_author":"https://pith.science/pith/E2UFGDHL2NTBSK4JBPAIXO2FD2/action/author_attestation","sign_citation":"https://pith.science/pith/E2UFGDHL2NTBSK4JBPAIXO2FD2/action/citation_signature","submit_replication":"https://pith.science/pith/E2UFGDHL2NTBSK4JBPAIXO2FD2/action/replication_record"}},"created_at":"2026-07-05T06:53:46.040259+00:00","updated_at":"2026-07-05T06:53:46.040259+00:00"}