{"id":"W3217374154","doi":"10.1109/jiot.2021.3131258","title":"A Fine-Grained Differentially Private Federated Learning Against Leakage From Gradients","year":2021,"lang":"en","type":"article","venue":"IEEE Internet of Things Journal","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":42,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of New Brunswick","funders":"Basic and Applied Basic Research Foundation of Guangdong Province; China Postdoctoral Science Foundation; National Natural Science Foundation of China","keywords":"Computer science; Differential privacy; Adversary; Leakage (economics); Federated learning; Deep learning; Information privacy; Private information retrieval; Data mining; Artificial intelligence; Distributed computing; Computer security","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":[0.003763773,0.001001836,0.0016781,0.0006337943,0.0009007659,0.001618905,0.00255066,0.002009981,0.001230985],"category_scores_gemma":[0.01257713,0.0004457291,0.0008884862,0.0009810176,0.001858989,0.004990557,0.004357224,0.002572265,0.0003787166],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001503994,"about_ca_system_score_gemma":0.002164956,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001548968,"about_ca_topic_score_gemma":0.001244809,"domain_scores_codex":[0.9962773,0.001175122,0.0002382889,0.0009025136,0.0009125158,0.0004943879],"domain_scores_gemma":[0.9946403,0.001763047,0.0004910559,0.002262008,0.0005972749,0.0002464116],"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":[0.001257133,0.0003889777,0.004138768,0.0001833639,0.0001668989,0.0003557013,0.0002982316,0.6642864,0.01564599,0.05664985,0.00638218,0.2502464],"study_design_scores_gemma":[0.00003084526,0.00006747943,0.0001504696,0.000008413251,0.00001170278,0.00008921542,0.00001421433,0.9730542,0.004297951,0.02178528,0.0004736363,0.00001649846],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04308826,0.0003198429,0.952863,0.0005658699,0.00005725997,0.00006810583,0.0001547221,0.001884227,0.0009987083],"genre_scores_gemma":[0.9000406,0.0001348473,0.09726442,0.0003940378,0.00004045064,0.00009324675,0.0001953307,0.00008583218,0.001751217],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003763773,"threshold_uncertainty_score":0.01990503,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02128934842707645,"score_gpt":0.2508348126022749,"score_spread":0.2295454641751984,"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."}}