{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:MVJEPA557QEZYBT7BWXPJJDS7H","short_pith_number":"pith:MVJEPA55","schema_version":"1.0","canonical_sha256":"65524783bdfc099c067f0daef4a472f9ebf2064ea9a90bc654bbd54c13ba6df9","source":{"kind":"arxiv","id":"2501.03119","version":3},"attestation_state":"computed","paper":{"title":"From Models to Network Topologies: A Topology Inference Attack in Decentralized Federated Learning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Alberto Huertas Celdran, Burkhard Stiller, Chao Feng, Gerome Bovet, Yuanzhe Gao","submitted_at":"2025-01-06T16:27:53Z","abstract_excerpt":"Federated Learning (FL) is widely recognized as a privacy-preserving Machine Learning paradigm due to its model-sharing mechanism that avoids direct data exchange. Nevertheless, model training leaves exploitable traces that can be used to infer sensitive information. In Decentralized FL (DFL), the topology, defining how participants are connected, plays a crucial role in shaping the model's privacy, robustness, and convergence. However, the topology introduces an unexplored vulnerability: attackers can exploit it to infer participant relationships and launch targeted attacks. This work uncover"},"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":"2501.03119","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-06T16:27:53Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c00e145ac9718908096a6fcde786d6ef68f1cf1a0abd24d09fb3c6c8c88137b2","abstract_canon_sha256":"4b2e319bf7b57ba78d5b7eee15e0efdb19df34fba41ff5a31557c90704be9c24"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:58:23.579538Z","signature_b64":"HlqFjWwd3z5fymgiQUMcrjp+AQsGIBv/nNaHfpmXFaU7dHZoTPW/YdYa0W5Bf22Dndb2oRq7LHFtJZpwjdH3Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"65524783bdfc099c067f0daef4a472f9ebf2064ea9a90bc654bbd54c13ba6df9","last_reissued_at":"2026-07-05T11:58:23.579099Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:58:23.579099Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"From Models to Network Topologies: A Topology Inference Attack in Decentralized Federated Learning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Alberto Huertas Celdran, Burkhard Stiller, Chao Feng, Gerome Bovet, Yuanzhe Gao","submitted_at":"2025-01-06T16:27:53Z","abstract_excerpt":"Federated Learning (FL) is widely recognized as a privacy-preserving Machine Learning paradigm due to its model-sharing mechanism that avoids direct data exchange. Nevertheless, model training leaves exploitable traces that can be used to infer sensitive information. In Decentralized FL (DFL), the topology, defining how participants are connected, plays a crucial role in shaping the model's privacy, robustness, and convergence. However, the topology introduces an unexplored vulnerability: attackers can exploit it to infer participant relationships and launch targeted attacks. This work uncover"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.03119","kind":"arxiv","version":3},"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/2501.03119/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":"2501.03119","created_at":"2026-07-05T11:58:23.579155+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.03119v3","created_at":"2026-07-05T11:58:23.579155+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.03119","created_at":"2026-07-05T11:58:23.579155+00:00"},{"alias_kind":"pith_short_12","alias_value":"MVJEPA557QEZ","created_at":"2026-07-05T11:58:23.579155+00:00"},{"alias_kind":"pith_short_16","alias_value":"MVJEPA557QEZYBT7","created_at":"2026-07-05T11:58:23.579155+00:00"},{"alias_kind":"pith_short_8","alias_value":"MVJEPA55","created_at":"2026-07-05T11:58:23.579155+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.19260","citing_title":"Topology-Aware Differential Privacy in Federated Learning","ref_index":33,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MVJEPA557QEZYBT7BWXPJJDS7H","json":"https://pith.science/pith/MVJEPA557QEZYBT7BWXPJJDS7H.json","graph_json":"https://pith.science/api/pith-number/MVJEPA557QEZYBT7BWXPJJDS7H/graph.json","events_json":"https://pith.science/api/pith-number/MVJEPA557QEZYBT7BWXPJJDS7H/events.json","paper":"https://pith.science/paper/MVJEPA55"},"agent_actions":{"view_html":"https://pith.science/pith/MVJEPA557QEZYBT7BWXPJJDS7H","download_json":"https://pith.science/pith/MVJEPA557QEZYBT7BWXPJJDS7H.json","view_paper":"https://pith.science/paper/MVJEPA55","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.03119&json=true","fetch_graph":"https://pith.science/api/pith-number/MVJEPA557QEZYBT7BWXPJJDS7H/graph.json","fetch_events":"https://pith.science/api/pith-number/MVJEPA557QEZYBT7BWXPJJDS7H/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MVJEPA557QEZYBT7BWXPJJDS7H/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MVJEPA557QEZYBT7BWXPJJDS7H/action/storage_attestation","attest_author":"https://pith.science/pith/MVJEPA557QEZYBT7BWXPJJDS7H/action/author_attestation","sign_citation":"https://pith.science/pith/MVJEPA557QEZYBT7BWXPJJDS7H/action/citation_signature","submit_replication":"https://pith.science/pith/MVJEPA557QEZYBT7BWXPJJDS7H/action/replication_record"}},"created_at":"2026-07-05T11:58:23.579155+00:00","updated_at":"2026-07-05T11:58:23.579155+00:00"}