{"id":"W4391897266","doi":"10.1016/j.sysarc.2024.103088","title":"Hybrid Privacy Preserving Federated Learning Against Irregular Users in Next-Generation Internet of Things","year":2024,"lang":"en","type":"article","venue":"Journal of Systems Architecture","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":99,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Calgary; Brandon University; University of Guelph","funders":"","keywords":"Computer science; Internet of Things; Internet privacy; The Internet; World Wide Web; 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":"codex-gemma-dda1882f352a","candidate_categories":["open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.001639183,0.0002250829,0.0004479936,0.000836388,0.00006566846,0.0008331401,0.009306232,0.0001353677,0.000003715984],"category_scores_gemma":[0.005855405,0.0001806144,0.0001310976,0.0006445575,0.00005436044,0.001699157,0.009826247,0.001313209,0.000003006397],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001874969,"about_ca_system_score_gemma":0.0001702883,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009414767,"about_ca_topic_score_gemma":0.000005681567,"domain_scores_codex":[0.9973487,0.0003446464,0.0009874511,0.0003721335,0.0006299882,0.0003171276],"domain_scores_gemma":[0.9974561,0.0002264071,0.000574341,0.001491245,0.0001771521,0.00007476455],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000112402,0.0002271695,0.003885012,0.003499694,0.0007933254,0.002803666,0.0131934,0.1246658,0.5089116,0.002539499,0.1259193,0.2134491],"study_design_scores_gemma":[0.0002889725,0.0001710907,0.0001459201,0.002797845,0.0000110625,0.0005878036,0.0001220168,0.9725261,0.01303709,0.004433755,0.005669853,0.0002084987],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5754097,0.004295682,0.4142026,0.004325432,0.001208127,0.0002073139,0.000002165195,0.0002058641,0.0001431131],"genre_scores_gemma":[0.9588223,0.0001024776,0.04075474,0.00004169856,0.0001756597,0.000004592773,0.000005416888,0.0000250589,0.00006804721],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8478603,"threshold_uncertainty_score":0.9981821,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03240004885923582,"score_gpt":0.2565090802461277,"score_spread":0.2241090313868919,"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."}}