{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:3NV23DOXFL3RQSTNHWJVUHGG56","short_pith_number":"pith:3NV23DOX","schema_version":"1.0","canonical_sha256":"db6bad8dd72af7184a6d3d935a1cc6ef92330c740b6ab63e76fcf9dc21c7df01","source":{"kind":"arxiv","id":"2210.13457","version":1},"attestation_state":"computed","paper":{"title":"Mixed Precision Quantization to Tackle Gradient Leakage Attacks in Federated Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CR","cs.CV"],"primary_cat":"cs.LG","authors_text":"Aryya Gangopadhyay, Emon Dey, Nirmalya Roy, Pretom Roy Ovi","submitted_at":"2022-10-22T04:24:32Z","abstract_excerpt":"Federated Learning (FL) enables collaborative model building among a large number of participants without the need for explicit data sharing. But this approach shows vulnerabilities when privacy inference attacks are applied to it. In particular, in the event of a gradient leakage attack, which has a higher success rate in retrieving sensitive data from the model gradients, FL models are at higher risk due to the presence of communication in their inherent architecture. The most alarming thing about this gradient leakage attack is that it can be performed in such a covert way that it does not "},"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":"2210.13457","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-10-22T04:24:32Z","cross_cats_sorted":["cs.AI","cs.CR","cs.CV"],"title_canon_sha256":"402f31970acea124e7e9ba37cefc05533bf7ac72dafeb5b0c5c76c4adb39432b","abstract_canon_sha256":"e30a02d5faa8b8214c8eb3d7c0c9fe3e1cfb20f5b566a3b523bbca00e17e7c20"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:10:18.642262Z","signature_b64":"kUQ24Ml4aETd2qrGiAGayzmHOP49LpJDVEX5f/eSEiLQVabyhHnsa6eAC2qR/Cca5nyl4vOKTCXYPKgiPnmPDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"db6bad8dd72af7184a6d3d935a1cc6ef92330c740b6ab63e76fcf9dc21c7df01","last_reissued_at":"2026-07-05T05:10:18.641784Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:10:18.641784Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Mixed Precision Quantization to Tackle Gradient Leakage Attacks in Federated Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CR","cs.CV"],"primary_cat":"cs.LG","authors_text":"Aryya Gangopadhyay, Emon Dey, Nirmalya Roy, Pretom Roy Ovi","submitted_at":"2022-10-22T04:24:32Z","abstract_excerpt":"Federated Learning (FL) enables collaborative model building among a large number of participants without the need for explicit data sharing. But this approach shows vulnerabilities when privacy inference attacks are applied to it. In particular, in the event of a gradient leakage attack, which has a higher success rate in retrieving sensitive data from the model gradients, FL models are at higher risk due to the presence of communication in their inherent architecture. The most alarming thing about this gradient leakage attack is that it can be performed in such a covert way that it does not "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.13457","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/2210.13457/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":"2210.13457","created_at":"2026-07-05T05:10:18.641843+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.13457v1","created_at":"2026-07-05T05:10:18.641843+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.13457","created_at":"2026-07-05T05:10:18.641843+00:00"},{"alias_kind":"pith_short_12","alias_value":"3NV23DOXFL3R","created_at":"2026-07-05T05:10:18.641843+00:00"},{"alias_kind":"pith_short_16","alias_value":"3NV23DOXFL3RQSTN","created_at":"2026-07-05T05:10:18.641843+00:00"},{"alias_kind":"pith_short_8","alias_value":"3NV23DOX","created_at":"2026-07-05T05:10:18.641843+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.26822","citing_title":"Quantization in Federated Learning: Methods, Challenges and Future Directions","ref_index":95,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3NV23DOXFL3RQSTNHWJVUHGG56","json":"https://pith.science/pith/3NV23DOXFL3RQSTNHWJVUHGG56.json","graph_json":"https://pith.science/api/pith-number/3NV23DOXFL3RQSTNHWJVUHGG56/graph.json","events_json":"https://pith.science/api/pith-number/3NV23DOXFL3RQSTNHWJVUHGG56/events.json","paper":"https://pith.science/paper/3NV23DOX"},"agent_actions":{"view_html":"https://pith.science/pith/3NV23DOXFL3RQSTNHWJVUHGG56","download_json":"https://pith.science/pith/3NV23DOXFL3RQSTNHWJVUHGG56.json","view_paper":"https://pith.science/paper/3NV23DOX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.13457&json=true","fetch_graph":"https://pith.science/api/pith-number/3NV23DOXFL3RQSTNHWJVUHGG56/graph.json","fetch_events":"https://pith.science/api/pith-number/3NV23DOXFL3RQSTNHWJVUHGG56/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3NV23DOXFL3RQSTNHWJVUHGG56/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3NV23DOXFL3RQSTNHWJVUHGG56/action/storage_attestation","attest_author":"https://pith.science/pith/3NV23DOXFL3RQSTNHWJVUHGG56/action/author_attestation","sign_citation":"https://pith.science/pith/3NV23DOXFL3RQSTNHWJVUHGG56/action/citation_signature","submit_replication":"https://pith.science/pith/3NV23DOXFL3RQSTNHWJVUHGG56/action/replication_record"}},"created_at":"2026-07-05T05:10:18.641843+00:00","updated_at":"2026-07-05T05:10:18.641843+00:00"}