{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:UBAIPV3T45CDFG5AQIPXJNWHFQ","short_pith_number":"pith:UBAIPV3T","schema_version":"1.0","canonical_sha256":"a04087d773e744329ba0821f74b6c72c01951cef7f3d5e1dbadb8c3a9597e24a","source":{"kind":"arxiv","id":"2203.01451","version":3},"attestation_state":"computed","paper":{"title":"Label Leakage and Protection from Forward Embedding in Vertical Federated Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR"],"primary_cat":"cs.LG","authors_text":"Chong Wang, Jiankai Sun, Xin Yang, Yuanshun Yao","submitted_at":"2022-03-02T22:54:54Z","abstract_excerpt":"Vertical federated learning (vFL) has gained much attention and been deployed to solve machine learning problems with data privacy concerns in recent years. However, some recent work demonstrated that vFL is vulnerable to privacy leakage even though only the forward intermediate embedding (rather than raw features) and backpropagated gradients (rather than raw labels) are communicated between the involved participants. As the raw labels often contain highly sensitive information, some recent work has been proposed to prevent the label leakage from the backpropagated gradients effectively in vF"},"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":"2203.01451","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-03-02T22:54:54Z","cross_cats_sorted":["cs.CR"],"title_canon_sha256":"11ebb8650ceed7d1f43b34cf861cded249c0afa84b8e3d9c95cf50a7113d4a58","abstract_canon_sha256":"559149b60fa725f440efcb4fe0680a86f247a26deeb37baae923404e8f63d8a3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:26:22.414426Z","signature_b64":"yHs2W6gzAe0CvYiF7zguLYMIQmNLccc6EgJBRyv601U+Nkq9YMG2VhclpuHrVmlpvqMkjN56s5zHQo7DdPL+BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a04087d773e744329ba0821f74b6c72c01951cef7f3d5e1dbadb8c3a9597e24a","last_reissued_at":"2026-07-05T04:26:22.413962Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:26:22.413962Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Label Leakage and Protection from Forward Embedding in Vertical Federated Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR"],"primary_cat":"cs.LG","authors_text":"Chong Wang, Jiankai Sun, Xin Yang, Yuanshun Yao","submitted_at":"2022-03-02T22:54:54Z","abstract_excerpt":"Vertical federated learning (vFL) has gained much attention and been deployed to solve machine learning problems with data privacy concerns in recent years. However, some recent work demonstrated that vFL is vulnerable to privacy leakage even though only the forward intermediate embedding (rather than raw features) and backpropagated gradients (rather than raw labels) are communicated between the involved participants. As the raw labels often contain highly sensitive information, some recent work has been proposed to prevent the label leakage from the backpropagated gradients effectively in vF"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.01451","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/2203.01451/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":"2203.01451","created_at":"2026-07-05T04:26:22.414014+00:00"},{"alias_kind":"arxiv_version","alias_value":"2203.01451v3","created_at":"2026-07-05T04:26:22.414014+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.01451","created_at":"2026-07-05T04:26:22.414014+00:00"},{"alias_kind":"pith_short_12","alias_value":"UBAIPV3T45CD","created_at":"2026-07-05T04:26:22.414014+00:00"},{"alias_kind":"pith_short_16","alias_value":"UBAIPV3T45CDFG5A","created_at":"2026-07-05T04:26:22.414014+00:00"},{"alias_kind":"pith_short_8","alias_value":"UBAIPV3T","created_at":"2026-07-05T04:26:22.414014+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2506.06742","citing_title":"LADSG: Label-Anonymized Distillation and Similar Gradient Substitution for Label Privacy in Vertical Federated Learning","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08343","citing_title":"Private Vertical Federated Inference for Time-Series","ref_index":18,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UBAIPV3T45CDFG5AQIPXJNWHFQ","json":"https://pith.science/pith/UBAIPV3T45CDFG5AQIPXJNWHFQ.json","graph_json":"https://pith.science/api/pith-number/UBAIPV3T45CDFG5AQIPXJNWHFQ/graph.json","events_json":"https://pith.science/api/pith-number/UBAIPV3T45CDFG5AQIPXJNWHFQ/events.json","paper":"https://pith.science/paper/UBAIPV3T"},"agent_actions":{"view_html":"https://pith.science/pith/UBAIPV3T45CDFG5AQIPXJNWHFQ","download_json":"https://pith.science/pith/UBAIPV3T45CDFG5AQIPXJNWHFQ.json","view_paper":"https://pith.science/paper/UBAIPV3T","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2203.01451&json=true","fetch_graph":"https://pith.science/api/pith-number/UBAIPV3T45CDFG5AQIPXJNWHFQ/graph.json","fetch_events":"https://pith.science/api/pith-number/UBAIPV3T45CDFG5AQIPXJNWHFQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UBAIPV3T45CDFG5AQIPXJNWHFQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UBAIPV3T45CDFG5AQIPXJNWHFQ/action/storage_attestation","attest_author":"https://pith.science/pith/UBAIPV3T45CDFG5AQIPXJNWHFQ/action/author_attestation","sign_citation":"https://pith.science/pith/UBAIPV3T45CDFG5AQIPXJNWHFQ/action/citation_signature","submit_replication":"https://pith.science/pith/UBAIPV3T45CDFG5AQIPXJNWHFQ/action/replication_record"}},"created_at":"2026-07-05T04:26:22.414014+00:00","updated_at":"2026-07-05T04:26:22.414014+00:00"}