{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:DUPNYNHFSLPCVAUOXOICAXGV5R","short_pith_number":"pith:DUPNYNHF","schema_version":"1.0","canonical_sha256":"1d1edc34e592de2a828ebb90205cd5ec72918cc4052a6d1b02206712a36d114c","source":{"kind":"arxiv","id":"2308.14658","version":1},"attestation_state":"computed","paper":{"title":"Adversarial Predictions of Data Distributions Across Federated Internet-of-Things Devices","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.DC"],"primary_cat":"cs.LG","authors_text":"Dario Dematties, Kyle Chard, Nathaniel Hudson, Nicola Ferrier, Peter Beckman, Rajesh Sankaran, Samir Rajani","submitted_at":"2023-08-28T15:40:50Z","abstract_excerpt":"Federated learning (FL) is increasingly becoming the default approach for training machine learning models across decentralized Internet-of-Things (IoT) devices. A key advantage of FL is that no raw data are communicated across the network, providing an immediate layer of privacy. Despite this, recent works have demonstrated that data reconstruction can be done with the locally trained model updates which are communicated across the network. However, many of these works have limitations with regard to how the gradients are computed in backpropagation. In this work, we demonstrate that the mode"},"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":"2308.14658","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-08-28T15:40:50Z","cross_cats_sorted":["cs.DC"],"title_canon_sha256":"6e17d908f9e50589eeb03c4d04f645f2b9e532c2b255e9f0c95a5fad82d4a9d1","abstract_canon_sha256":"6553dcce1650b8b4d2b64e684eb1b9aa04adf5e10795add571d06b69db3ffbfa"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:45:29.280235Z","signature_b64":"GR8UyfQVRquYkYtGUbtFem//gR/b+TiwG1KVOMiQ5HRgMgHB2sLLakg6IgEGas+9mh+8FKppsOAz1hAwajlADw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1d1edc34e592de2a828ebb90205cd5ec72918cc4052a6d1b02206712a36d114c","last_reissued_at":"2026-07-05T06:45:29.279822Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:45:29.279822Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Adversarial Predictions of Data Distributions Across Federated Internet-of-Things Devices","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.DC"],"primary_cat":"cs.LG","authors_text":"Dario Dematties, Kyle Chard, Nathaniel Hudson, Nicola Ferrier, Peter Beckman, Rajesh Sankaran, Samir Rajani","submitted_at":"2023-08-28T15:40:50Z","abstract_excerpt":"Federated learning (FL) is increasingly becoming the default approach for training machine learning models across decentralized Internet-of-Things (IoT) devices. A key advantage of FL is that no raw data are communicated across the network, providing an immediate layer of privacy. Despite this, recent works have demonstrated that data reconstruction can be done with the locally trained model updates which are communicated across the network. However, many of these works have limitations with regard to how the gradients are computed in backpropagation. In this work, we demonstrate that the mode"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.14658","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/2308.14658/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":"2308.14658","created_at":"2026-07-05T06:45:29.279880+00:00"},{"alias_kind":"arxiv_version","alias_value":"2308.14658v1","created_at":"2026-07-05T06:45:29.279880+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.14658","created_at":"2026-07-05T06:45:29.279880+00:00"},{"alias_kind":"pith_short_12","alias_value":"DUPNYNHFSLPC","created_at":"2026-07-05T06:45:29.279880+00:00"},{"alias_kind":"pith_short_16","alias_value":"DUPNYNHFSLPCVAUO","created_at":"2026-07-05T06:45:29.279880+00:00"},{"alias_kind":"pith_short_8","alias_value":"DUPNYNHF","created_at":"2026-07-05T06:45:29.279880+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/DUPNYNHFSLPCVAUOXOICAXGV5R","json":"https://pith.science/pith/DUPNYNHFSLPCVAUOXOICAXGV5R.json","graph_json":"https://pith.science/api/pith-number/DUPNYNHFSLPCVAUOXOICAXGV5R/graph.json","events_json":"https://pith.science/api/pith-number/DUPNYNHFSLPCVAUOXOICAXGV5R/events.json","paper":"https://pith.science/paper/DUPNYNHF"},"agent_actions":{"view_html":"https://pith.science/pith/DUPNYNHFSLPCVAUOXOICAXGV5R","download_json":"https://pith.science/pith/DUPNYNHFSLPCVAUOXOICAXGV5R.json","view_paper":"https://pith.science/paper/DUPNYNHF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2308.14658&json=true","fetch_graph":"https://pith.science/api/pith-number/DUPNYNHFSLPCVAUOXOICAXGV5R/graph.json","fetch_events":"https://pith.science/api/pith-number/DUPNYNHFSLPCVAUOXOICAXGV5R/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DUPNYNHFSLPCVAUOXOICAXGV5R/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DUPNYNHFSLPCVAUOXOICAXGV5R/action/storage_attestation","attest_author":"https://pith.science/pith/DUPNYNHFSLPCVAUOXOICAXGV5R/action/author_attestation","sign_citation":"https://pith.science/pith/DUPNYNHFSLPCVAUOXOICAXGV5R/action/citation_signature","submit_replication":"https://pith.science/pith/DUPNYNHFSLPCVAUOXOICAXGV5R/action/replication_record"}},"created_at":"2026-07-05T06:45:29.279880+00:00","updated_at":"2026-07-05T06:45:29.279880+00:00"}