{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:YJQH34A6PZW2JQQBCQZ7C65EH4","short_pith_number":"pith:YJQH34A6","schema_version":"1.0","canonical_sha256":"c2607df01e7e6da4c2011433f17ba43f3d568af07333ceb3edc41d455bbe03ea","source":{"kind":"arxiv","id":"2011.12505","version":2},"attestation_state":"computed","paper":{"title":"Privacy-preserving Collaborative Learning with Automatic Transformation Search","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Han Qiu, Shangwei Guo, Tianwei Zhang, Wei Gao, Yang Liu, Yonggang Wen","submitted_at":"2020-11-25T03:56:54Z","abstract_excerpt":"Collaborative learning has gained great popularity due to its benefit of data privacy protection: participants can jointly train a Deep Learning model without sharing their training sets. However, recent works discovered that an adversary can fully recover the sensitive training samples from the shared gradients. Such reconstruction attacks pose severe threats to collaborative learning. Hence, effective mitigation solutions are urgently desired.\n  In this paper, we propose to leverage data augmentation to defeat reconstruction attacks: by preprocessing sensitive images with carefully-selected "},"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":"2011.12505","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-11-25T03:56:54Z","cross_cats_sorted":[],"title_canon_sha256":"fb0ecd8bff94946ae8fc7f5d48d77119c07489ad57cf33c87e49d484d563cc1f","abstract_canon_sha256":"880952485b7bc14ab504ee475bf89e9d0a0306d23ac1a0567c4cd837e44fd9e4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:26:52.398067Z","signature_b64":"xsOCrAew1ZrjDKcFDvPYa5lcJ3ypeHshXyaCapMy2oyBQDmAE3APNKfv1UQN92AVZOMvuyEp4ly7XSITTWZeAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c2607df01e7e6da4c2011433f17ba43f3d568af07333ceb3edc41d455bbe03ea","last_reissued_at":"2026-07-05T02:26:52.397648Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:26:52.397648Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Privacy-preserving Collaborative Learning with Automatic Transformation Search","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Han Qiu, Shangwei Guo, Tianwei Zhang, Wei Gao, Yang Liu, Yonggang Wen","submitted_at":"2020-11-25T03:56:54Z","abstract_excerpt":"Collaborative learning has gained great popularity due to its benefit of data privacy protection: participants can jointly train a Deep Learning model without sharing their training sets. However, recent works discovered that an adversary can fully recover the sensitive training samples from the shared gradients. Such reconstruction attacks pose severe threats to collaborative learning. Hence, effective mitigation solutions are urgently desired.\n  In this paper, we propose to leverage data augmentation to defeat reconstruction attacks: by preprocessing sensitive images with carefully-selected "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.12505","kind":"arxiv","version":2},"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/2011.12505/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":"2011.12505","created_at":"2026-07-05T02:26:52.397708+00:00"},{"alias_kind":"arxiv_version","alias_value":"2011.12505v2","created_at":"2026-07-05T02:26:52.397708+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.12505","created_at":"2026-07-05T02:26:52.397708+00:00"},{"alias_kind":"pith_short_12","alias_value":"YJQH34A6PZW2","created_at":"2026-07-05T02:26:52.397708+00:00"},{"alias_kind":"pith_short_16","alias_value":"YJQH34A6PZW2JQQB","created_at":"2026-07-05T02:26:52.397708+00:00"},{"alias_kind":"pith_short_8","alias_value":"YJQH34A6","created_at":"2026-07-05T02:26:52.397708+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/YJQH34A6PZW2JQQBCQZ7C65EH4","json":"https://pith.science/pith/YJQH34A6PZW2JQQBCQZ7C65EH4.json","graph_json":"https://pith.science/api/pith-number/YJQH34A6PZW2JQQBCQZ7C65EH4/graph.json","events_json":"https://pith.science/api/pith-number/YJQH34A6PZW2JQQBCQZ7C65EH4/events.json","paper":"https://pith.science/paper/YJQH34A6"},"agent_actions":{"view_html":"https://pith.science/pith/YJQH34A6PZW2JQQBCQZ7C65EH4","download_json":"https://pith.science/pith/YJQH34A6PZW2JQQBCQZ7C65EH4.json","view_paper":"https://pith.science/paper/YJQH34A6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2011.12505&json=true","fetch_graph":"https://pith.science/api/pith-number/YJQH34A6PZW2JQQBCQZ7C65EH4/graph.json","fetch_events":"https://pith.science/api/pith-number/YJQH34A6PZW2JQQBCQZ7C65EH4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YJQH34A6PZW2JQQBCQZ7C65EH4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YJQH34A6PZW2JQQBCQZ7C65EH4/action/storage_attestation","attest_author":"https://pith.science/pith/YJQH34A6PZW2JQQBCQZ7C65EH4/action/author_attestation","sign_citation":"https://pith.science/pith/YJQH34A6PZW2JQQBCQZ7C65EH4/action/citation_signature","submit_replication":"https://pith.science/pith/YJQH34A6PZW2JQQBCQZ7C65EH4/action/replication_record"}},"created_at":"2026-07-05T02:26:52.397708+00:00","updated_at":"2026-07-05T02:26:52.397708+00:00"}