{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:4724ALWDHTDC6LFAIVZCJGIXQR","short_pith_number":"pith:4724ALWD","schema_version":"1.0","canonical_sha256":"e7f5c02ec33cc62f2ca045722499178463fb6a82dea6b2932e6aefea23b9ca13","source":{"kind":"arxiv","id":"2003.02133","version":1},"attestation_state":"computed","paper":{"title":"Threats to Federated Learning: A Survey","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CR","authors_text":"Han Yu, Lingjuan Lyu, Qiang Yang","submitted_at":"2020-03-04T15:30:10Z","abstract_excerpt":"With the emergence of data silos and popular privacy awareness, the traditional centralized approach of training artificial intelligence (AI) models is facing strong challenges. Federated learning (FL) has recently emerged as a promising solution under this new reality. Existing FL protocol design has been shown to exhibit vulnerabilities which can be exploited by adversaries both within and without the system to compromise data privacy. It is thus of paramount importance to make FL system designers to be aware of the implications of future FL algorithm design on privacy-preservation. Currentl"},"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":"2003.02133","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2020-03-04T15:30:10Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"591208cea2ecc081dce53d7ab2bd0aee12a20669581a70ec1531ed22b0e0b079","abstract_canon_sha256":"7ea9f32cb75146088392a64c7b35b4b0a91fc12c75b9f75f52eaefd7d4f8b8d5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:45:47.046136Z","signature_b64":"zRYYGkdA6Zb/EeRRXNGAhBrj67dL4qLYJDkZCOBeKfLmC0y1YooiGgB6kWjjloz76KpcLVcFA7CsN8PJUg8ABw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e7f5c02ec33cc62f2ca045722499178463fb6a82dea6b2932e6aefea23b9ca13","last_reissued_at":"2026-07-05T00:45:47.045766Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:45:47.045766Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Threats to Federated Learning: A Survey","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CR","authors_text":"Han Yu, Lingjuan Lyu, Qiang Yang","submitted_at":"2020-03-04T15:30:10Z","abstract_excerpt":"With the emergence of data silos and popular privacy awareness, the traditional centralized approach of training artificial intelligence (AI) models is facing strong challenges. Federated learning (FL) has recently emerged as a promising solution under this new reality. Existing FL protocol design has been shown to exhibit vulnerabilities which can be exploited by adversaries both within and without the system to compromise data privacy. It is thus of paramount importance to make FL system designers to be aware of the implications of future FL algorithm design on privacy-preservation. Currentl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2003.02133","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/2003.02133/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":"2003.02133","created_at":"2026-07-05T00:45:47.045826+00:00"},{"alias_kind":"arxiv_version","alias_value":"2003.02133v1","created_at":"2026-07-05T00:45:47.045826+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2003.02133","created_at":"2026-07-05T00:45:47.045826+00:00"},{"alias_kind":"pith_short_12","alias_value":"4724ALWDHTDC","created_at":"2026-07-05T00:45:47.045826+00:00"},{"alias_kind":"pith_short_16","alias_value":"4724ALWDHTDC6LFA","created_at":"2026-07-05T00:45:47.045826+00:00"},{"alias_kind":"pith_short_8","alias_value":"4724ALWD","created_at":"2026-07-05T00:45:47.045826+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2509.06896","citing_title":"Are Targeted Data Poisoning Attacks as Effective as We Think?","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2407.15389","citing_title":"Poisoning with A Pill: Circumventing Detection in Federated Learning","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2505.06907","citing_title":"A Survey on Foundation Models for Personalized Federated Intelligence","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15520","citing_title":"On the Fragility of Data Attribution When Learning Is Distributed","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2511.14715","citing_title":"FLARE: Adaptive Multi-Dimensional Reputation for Robust Client Reliability in Federated Learning","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2605.03069","citing_title":"Distributed Deep Variational Approach for Privacy-preserving Data Release","ref_index":57,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4724ALWDHTDC6LFAIVZCJGIXQR","json":"https://pith.science/pith/4724ALWDHTDC6LFAIVZCJGIXQR.json","graph_json":"https://pith.science/api/pith-number/4724ALWDHTDC6LFAIVZCJGIXQR/graph.json","events_json":"https://pith.science/api/pith-number/4724ALWDHTDC6LFAIVZCJGIXQR/events.json","paper":"https://pith.science/paper/4724ALWD"},"agent_actions":{"view_html":"https://pith.science/pith/4724ALWDHTDC6LFAIVZCJGIXQR","download_json":"https://pith.science/pith/4724ALWDHTDC6LFAIVZCJGIXQR.json","view_paper":"https://pith.science/paper/4724ALWD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2003.02133&json=true","fetch_graph":"https://pith.science/api/pith-number/4724ALWDHTDC6LFAIVZCJGIXQR/graph.json","fetch_events":"https://pith.science/api/pith-number/4724ALWDHTDC6LFAIVZCJGIXQR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4724ALWDHTDC6LFAIVZCJGIXQR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4724ALWDHTDC6LFAIVZCJGIXQR/action/storage_attestation","attest_author":"https://pith.science/pith/4724ALWDHTDC6LFAIVZCJGIXQR/action/author_attestation","sign_citation":"https://pith.science/pith/4724ALWDHTDC6LFAIVZCJGIXQR/action/citation_signature","submit_replication":"https://pith.science/pith/4724ALWDHTDC6LFAIVZCJGIXQR/action/replication_record"}},"created_at":"2026-07-05T00:45:47.045826+00:00","updated_at":"2026-07-05T00:45:47.045826+00:00"}