{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:IOJFV4PEK6YOZOZW5PETZQJYHM","short_pith_number":"pith:IOJFV4PE","schema_version":"1.0","canonical_sha256":"43925af1e457b0ecbb36ebc93cc1383b1b078f2f68082de7232513279e71d203","source":{"kind":"arxiv","id":"2006.14170","version":1},"attestation_state":"computed","paper":{"title":"Towards Differentially Private Text Representations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.CR","stat.ML"],"primary_cat":"cs.LG","authors_text":"Lingjuan Lyu, Tong Xiao, Xuanli He, Yitong Li","submitted_at":"2020-06-25T04:42:18Z","abstract_excerpt":"Most deep learning frameworks require users to pool their local data or model updates to a trusted server to train or maintain a global model. The assumption of a trusted server who has access to user information is ill-suited in many applications. To tackle this problem, we develop a new deep learning framework under an untrusted server setting, which includes three modules: (1) embedding module, (2) randomization module, and (3) classifier module. For the randomization module, we propose a novel local differentially private (LDP) protocol to reduce the impact of privacy parameter $\\epsilon$ "},"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":"2006.14170","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-25T04:42:18Z","cross_cats_sorted":["cs.CL","cs.CR","stat.ML"],"title_canon_sha256":"5aa265ff9327104019c115bb154a5156c0fbcff051a25a3f95cf40980ec33641","abstract_canon_sha256":"36f8839c81fca443852c60e331a9461f80d041c72e21a7a7c9bb0b129e885b19"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:13:29.786632Z","signature_b64":"/vx7CoMMUxBabNsZl2FxljZHzRWFO2GHDT+9AsHjJC3b29SufiVsjIwN7BtvkhoRX+oQMRRBmIsvRCe11lKQCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"43925af1e457b0ecbb36ebc93cc1383b1b078f2f68082de7232513279e71d203","last_reissued_at":"2026-07-05T01:13:29.786170Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:13:29.786170Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards Differentially Private Text Representations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.CR","stat.ML"],"primary_cat":"cs.LG","authors_text":"Lingjuan Lyu, Tong Xiao, Xuanli He, Yitong Li","submitted_at":"2020-06-25T04:42:18Z","abstract_excerpt":"Most deep learning frameworks require users to pool their local data or model updates to a trusted server to train or maintain a global model. The assumption of a trusted server who has access to user information is ill-suited in many applications. To tackle this problem, we develop a new deep learning framework under an untrusted server setting, which includes three modules: (1) embedding module, (2) randomization module, and (3) classifier module. For the randomization module, we propose a novel local differentially private (LDP) protocol to reduce the impact of privacy parameter $\\epsilon$ "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.14170","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/2006.14170/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":"2006.14170","created_at":"2026-07-05T01:13:29.786232+00:00"},{"alias_kind":"arxiv_version","alias_value":"2006.14170v1","created_at":"2026-07-05T01:13:29.786232+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.14170","created_at":"2026-07-05T01:13:29.786232+00:00"},{"alias_kind":"pith_short_12","alias_value":"IOJFV4PEK6YO","created_at":"2026-07-05T01:13:29.786232+00:00"},{"alias_kind":"pith_short_16","alias_value":"IOJFV4PEK6YOZOZW","created_at":"2026-07-05T01:13:29.786232+00:00"},{"alias_kind":"pith_short_8","alias_value":"IOJFV4PE","created_at":"2026-07-05T01:13:29.786232+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/IOJFV4PEK6YOZOZW5PETZQJYHM","json":"https://pith.science/pith/IOJFV4PEK6YOZOZW5PETZQJYHM.json","graph_json":"https://pith.science/api/pith-number/IOJFV4PEK6YOZOZW5PETZQJYHM/graph.json","events_json":"https://pith.science/api/pith-number/IOJFV4PEK6YOZOZW5PETZQJYHM/events.json","paper":"https://pith.science/paper/IOJFV4PE"},"agent_actions":{"view_html":"https://pith.science/pith/IOJFV4PEK6YOZOZW5PETZQJYHM","download_json":"https://pith.science/pith/IOJFV4PEK6YOZOZW5PETZQJYHM.json","view_paper":"https://pith.science/paper/IOJFV4PE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2006.14170&json=true","fetch_graph":"https://pith.science/api/pith-number/IOJFV4PEK6YOZOZW5PETZQJYHM/graph.json","fetch_events":"https://pith.science/api/pith-number/IOJFV4PEK6YOZOZW5PETZQJYHM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IOJFV4PEK6YOZOZW5PETZQJYHM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IOJFV4PEK6YOZOZW5PETZQJYHM/action/storage_attestation","attest_author":"https://pith.science/pith/IOJFV4PEK6YOZOZW5PETZQJYHM/action/author_attestation","sign_citation":"https://pith.science/pith/IOJFV4PEK6YOZOZW5PETZQJYHM/action/citation_signature","submit_replication":"https://pith.science/pith/IOJFV4PEK6YOZOZW5PETZQJYHM/action/replication_record"}},"created_at":"2026-07-05T01:13:29.786232+00:00","updated_at":"2026-07-05T01:13:29.786232+00:00"}