{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:36QIL4QD2YAYQP2NQMQZ2SE2QB","short_pith_number":"pith:36QIL4QD","schema_version":"1.0","canonical_sha256":"dfa085f203d601883f4d83219d489a8040382b2fe930b75ebfdb4194ad352a9c","source":{"kind":"arxiv","id":"2404.16850","version":1},"attestation_state":"computed","paper":{"title":"Membership Information Leakage in Federated Contrastive Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CR","authors_text":"Kongyang Chen, Wangjun Zhang, Wenfeng Wang, Yao Huang, Zhipeng Li, Zixin Wang","submitted_at":"2024-03-06T19:53:25Z","abstract_excerpt":"Federated Contrastive Learning (FCL) represents a burgeoning approach for learning from decentralized unlabeled data while upholding data privacy. In FCL, participant clients collaborate in learning a global encoder using unlabeled data, which can serve as a versatile feature extractor for diverse downstream tasks. Nonetheless, FCL is susceptible to privacy risks, such as membership information leakage, stemming from its distributed nature, an aspect often overlooked in current solutions. This study delves into the feasibility of executing a membership inference attack on FCL and proposes a ro"},"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":"2404.16850","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2024-03-06T19:53:25Z","cross_cats_sorted":[],"title_canon_sha256":"4a0f6ceef2bab2012c4270cfa4b0487840816480fbdc794fdaed01205a3d49cc","abstract_canon_sha256":"46db2afabe2c03613599f43155a7796a2b4148f4e80e07ad4b1b6826a52cb4b9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:12:16.001271Z","signature_b64":"rA2RzYI0EStyc7tAf35u/tAiWYgzAgI7rIZHU9gkJ9G8A0hoWwdDW1Y/TF8PVfwCTm576xmHqRfcSB/cMoT7BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dfa085f203d601883f4d83219d489a8040382b2fe930b75ebfdb4194ad352a9c","last_reissued_at":"2026-07-05T08:12:16.000904Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:12:16.000904Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Membership Information Leakage in Federated Contrastive Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CR","authors_text":"Kongyang Chen, Wangjun Zhang, Wenfeng Wang, Yao Huang, Zhipeng Li, Zixin Wang","submitted_at":"2024-03-06T19:53:25Z","abstract_excerpt":"Federated Contrastive Learning (FCL) represents a burgeoning approach for learning from decentralized unlabeled data while upholding data privacy. In FCL, participant clients collaborate in learning a global encoder using unlabeled data, which can serve as a versatile feature extractor for diverse downstream tasks. Nonetheless, FCL is susceptible to privacy risks, such as membership information leakage, stemming from its distributed nature, an aspect often overlooked in current solutions. This study delves into the feasibility of executing a membership inference attack on FCL and proposes a ro"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.16850","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/2404.16850/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":"2404.16850","created_at":"2026-07-05T08:12:16.000964+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.16850v1","created_at":"2026-07-05T08:12:16.000964+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.16850","created_at":"2026-07-05T08:12:16.000964+00:00"},{"alias_kind":"pith_short_12","alias_value":"36QIL4QD2YAY","created_at":"2026-07-05T08:12:16.000964+00:00"},{"alias_kind":"pith_short_16","alias_value":"36QIL4QD2YAYQP2N","created_at":"2026-07-05T08:12:16.000964+00:00"},{"alias_kind":"pith_short_8","alias_value":"36QIL4QD","created_at":"2026-07-05T08:12:16.000964+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/36QIL4QD2YAYQP2NQMQZ2SE2QB","json":"https://pith.science/pith/36QIL4QD2YAYQP2NQMQZ2SE2QB.json","graph_json":"https://pith.science/api/pith-number/36QIL4QD2YAYQP2NQMQZ2SE2QB/graph.json","events_json":"https://pith.science/api/pith-number/36QIL4QD2YAYQP2NQMQZ2SE2QB/events.json","paper":"https://pith.science/paper/36QIL4QD"},"agent_actions":{"view_html":"https://pith.science/pith/36QIL4QD2YAYQP2NQMQZ2SE2QB","download_json":"https://pith.science/pith/36QIL4QD2YAYQP2NQMQZ2SE2QB.json","view_paper":"https://pith.science/paper/36QIL4QD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.16850&json=true","fetch_graph":"https://pith.science/api/pith-number/36QIL4QD2YAYQP2NQMQZ2SE2QB/graph.json","fetch_events":"https://pith.science/api/pith-number/36QIL4QD2YAYQP2NQMQZ2SE2QB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/36QIL4QD2YAYQP2NQMQZ2SE2QB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/36QIL4QD2YAYQP2NQMQZ2SE2QB/action/storage_attestation","attest_author":"https://pith.science/pith/36QIL4QD2YAYQP2NQMQZ2SE2QB/action/author_attestation","sign_citation":"https://pith.science/pith/36QIL4QD2YAYQP2NQMQZ2SE2QB/action/citation_signature","submit_replication":"https://pith.science/pith/36QIL4QD2YAYQP2NQMQZ2SE2QB/action/replication_record"}},"created_at":"2026-07-05T08:12:16.000964+00:00","updated_at":"2026-07-05T08:12:16.000964+00:00"}