{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:QH3YAUGOIQ3A3LBNVEAN7YHTNL","short_pith_number":"pith:QH3YAUGO","schema_version":"1.0","canonical_sha256":"81f78050ce44360dac2da900dfe0f36ad52686d00f3e3426ec8b91d402cdedde","source":{"kind":"arxiv","id":"2011.05578","version":1},"attestation_state":"computed","paper":{"title":"Compression Boosts Differentially Private Federated Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR"],"primary_cat":"cs.LG","authors_text":"Claude Castelluccia, Gergely \\'Acs, Pierre Genev\\`es, Raouf Kerkouche","submitted_at":"2020-11-10T13:11:03Z","abstract_excerpt":"Federated Learning allows distributed entities to train a common model collaboratively without sharing their own data. Although it prevents data collection and aggregation by exchanging only parameter updates, it remains vulnerable to various inference and reconstruction attacks where a malicious entity can learn private information about the participants' training data from the captured gradients. Differential Privacy is used to obtain theoretically sound privacy guarantees against such inference attacks by noising the exchanged update vectors. However, the added noise is proportional to the "},"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":"2011.05578","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-11-10T13:11:03Z","cross_cats_sorted":["cs.CR"],"title_canon_sha256":"bc755fe7e4963f8db2f70f5bcd06aeabf60de6d0c7a23712befc60503532e7cc","abstract_canon_sha256":"7158a40dd636e46cfd5f6c53471144d3e6bef84aaf1a58c5725a25916db648c4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:50:51.407080Z","signature_b64":"SuaXll4SS3SIgdv754trLumXWpf392hFlVBeSYJ93e0ava4znOQA2QhJ0O9vrOWPiDph0YP4UrdL1JWqunTfDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"81f78050ce44360dac2da900dfe0f36ad52686d00f3e3426ec8b91d402cdedde","last_reissued_at":"2026-07-05T01:50:51.406741Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:50:51.406741Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Compression Boosts Differentially Private Federated Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR"],"primary_cat":"cs.LG","authors_text":"Claude Castelluccia, Gergely \\'Acs, Pierre Genev\\`es, Raouf Kerkouche","submitted_at":"2020-11-10T13:11:03Z","abstract_excerpt":"Federated Learning allows distributed entities to train a common model collaboratively without sharing their own data. Although it prevents data collection and aggregation by exchanging only parameter updates, it remains vulnerable to various inference and reconstruction attacks where a malicious entity can learn private information about the participants' training data from the captured gradients. Differential Privacy is used to obtain theoretically sound privacy guarantees against such inference attacks by noising the exchanged update vectors. However, the added noise is proportional to the "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.05578","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/2011.05578/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":"2011.05578","created_at":"2026-07-05T01:50:51.406797+00:00"},{"alias_kind":"arxiv_version","alias_value":"2011.05578v1","created_at":"2026-07-05T01:50:51.406797+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.05578","created_at":"2026-07-05T01:50:51.406797+00:00"},{"alias_kind":"pith_short_12","alias_value":"QH3YAUGOIQ3A","created_at":"2026-07-05T01:50:51.406797+00:00"},{"alias_kind":"pith_short_16","alias_value":"QH3YAUGOIQ3A3LBN","created_at":"2026-07-05T01:50:51.406797+00:00"},{"alias_kind":"pith_short_8","alias_value":"QH3YAUGO","created_at":"2026-07-05T01:50:51.406797+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/QH3YAUGOIQ3A3LBNVEAN7YHTNL","json":"https://pith.science/pith/QH3YAUGOIQ3A3LBNVEAN7YHTNL.json","graph_json":"https://pith.science/api/pith-number/QH3YAUGOIQ3A3LBNVEAN7YHTNL/graph.json","events_json":"https://pith.science/api/pith-number/QH3YAUGOIQ3A3LBNVEAN7YHTNL/events.json","paper":"https://pith.science/paper/QH3YAUGO"},"agent_actions":{"view_html":"https://pith.science/pith/QH3YAUGOIQ3A3LBNVEAN7YHTNL","download_json":"https://pith.science/pith/QH3YAUGOIQ3A3LBNVEAN7YHTNL.json","view_paper":"https://pith.science/paper/QH3YAUGO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2011.05578&json=true","fetch_graph":"https://pith.science/api/pith-number/QH3YAUGOIQ3A3LBNVEAN7YHTNL/graph.json","fetch_events":"https://pith.science/api/pith-number/QH3YAUGOIQ3A3LBNVEAN7YHTNL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QH3YAUGOIQ3A3LBNVEAN7YHTNL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QH3YAUGOIQ3A3LBNVEAN7YHTNL/action/storage_attestation","attest_author":"https://pith.science/pith/QH3YAUGOIQ3A3LBNVEAN7YHTNL/action/author_attestation","sign_citation":"https://pith.science/pith/QH3YAUGOIQ3A3LBNVEAN7YHTNL/action/citation_signature","submit_replication":"https://pith.science/pith/QH3YAUGOIQ3A3LBNVEAN7YHTNL/action/replication_record"}},"created_at":"2026-07-05T01:50:51.406797+00:00","updated_at":"2026-07-05T01:50:51.406797+00:00"}