{"id":"W4206998261","doi":"10.1109/gcwkshps52748.2021.9682053","title":"Secure Aggregation in Federated Learning via Multiparty Homomorphic Encryption","year":2021,"lang":"en","type":"article","venue":"2021 IEEE Globecom Workshops (GC Wkshps)","topic":"Cryptography and Data Security","field":"Computer Science","cited_by":31,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Homomorphic encryption; Correctness; Encryption; Node (physics); Homomorphic secret sharing; Scheme (mathematics); Key (lock); Theoretical computer science; Learning with errors; Secure multi-party computation; Aggregate (composite); Distributed computing; Computation; Algorithm; Computer network; Computer security; Mathematics","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006838784,0.0003755286,0.0004288998,0.0002778062,0.0004452727,0.0007182035,0.0006588483,0.0003358001,0.0003525516],"category_scores_gemma":[0.0002193206,0.0004176362,0.0002059624,0.003155382,0.00007447237,0.001324799,0.0003081745,0.000983594,0.0002810319],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001427764,"about_ca_system_score_gemma":0.0001936848,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001484763,"about_ca_topic_score_gemma":0.001689933,"domain_scores_codex":[0.9964993,0.0005867702,0.0006155332,0.001074188,0.0005348934,0.0006892969],"domain_scores_gemma":[0.9982011,0.0002553617,0.0002296379,0.0008048949,0.0002927137,0.0002163066],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002128322,0.002372474,0.04916092,0.0002522123,0.0002916784,0.002864338,0.008508822,0.01977008,0.02460973,0.04507484,0.01673781,0.8301443],"study_design_scores_gemma":[0.005378949,0.0002312833,0.04488172,0.000964036,0.00008083192,0.0004625553,0.001600078,0.8438485,0.02260839,0.02619135,0.05094589,0.002806381],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2450985,0.001657369,0.7484794,0.001207108,0.001825879,0.000357526,0.00001790011,0.0004748792,0.000881403],"genre_scores_gemma":[0.9809719,0.0004700601,0.01760656,0.0003215767,0.000260736,0.00004685683,0.0002024491,0.0000322652,0.00008760011],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8273379,"threshold_uncertainty_score":0.9998276,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01164605868932145,"score_gpt":0.2357756032319282,"score_spread":0.2241295445426068,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}