{"id":"W3185400193","doi":"10.48550/arxiv.2004.02264","title":"PrivFL: Practical Privacy-preserving Federated Regressions on High-dimensional Data over Mobile Networks","year":2020,"lang":"en","type":"preprint","venue":"IACR Cryptology ePrint Archive","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Homomorphic encryption; Encryption; Protocol (science); Federated learning; Information privacy; Semantic security; Scheme (mathematics); Robustness (evolution); Computer network; Machine learning; Artificial intelligence; Computer security; Public-key cryptography","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005190976,0.000877868,0.001199421,0.0004956597,0.00100348,0.001806904,0.002454356,0.001933563,0.001682147],"category_scores_gemma":[0.01662051,0.0006102266,0.0009920445,0.0008137026,0.001692695,0.005685015,0.005242871,0.002861069,0.0008633783],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001060792,"about_ca_system_score_gemma":0.001526289,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001331108,"about_ca_topic_score_gemma":0.001175897,"domain_scores_codex":[0.9954248,0.001982379,0.0002692937,0.0008758877,0.001023325,0.0004242831],"domain_scores_gemma":[0.9914427,0.003490943,0.0007110987,0.003704989,0.0004624157,0.0001877531],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001259231,0.0003301312,0.00389973,0.0002242101,0.0001674519,0.0006948819,0.000585456,0.6778781,0.01569733,0.08626457,0.008222296,0.2047766],"study_design_scores_gemma":[0.00003473894,0.00005164765,0.0001955931,0.000008275676,0.000007019042,0.00008567481,0.00003015482,0.9660868,0.005405868,0.02720499,0.0008749772,0.00001428071],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02596013,0.0001192938,0.9688292,0.0004589768,0.00002452742,0.0000604323,0.0001566586,0.003819037,0.0005719538],"genre_scores_gemma":[0.8515768,0.0001521886,0.1445615,0.0003909005,0.00004771039,0.0001806669,0.0004626353,0.0002337961,0.00239373],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.005190976,"threshold_uncertainty_score":0.02745289,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07637538680421993,"score_gpt":0.3490333168209711,"score_spread":0.2726579300167511,"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."}}