{"id":"W3211643445","doi":"10.1109/jiot.2021.3127886","title":"Lightweight Federated Learning for Large-Scale IoT Devices With Privacy Guarantee","year":2021,"lang":"en","type":"article","venue":"IEEE Internet of Things Journal","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":41,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Windsor","funders":"Fundamental Research Funds for the Central Universities; National Key Research and Development Program of China; National Natural Science Foundation of China","keywords":"Computer science; Scheme (mathematics); Collusion; Software deployment; Cryptography; Key (lock); Information privacy; Computer security; Distributed computing; Security analysis; Internet of Things; Computer network","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":[0.0008443319,0.0002360048,0.0003851352,0.0001916357,0.000246014,0.0007552435,0.01252196,0.0001510677,0.00003796014],"category_scores_gemma":[0.004030365,0.0001874446,0.0001428716,0.0003918349,0.0000631388,0.001191388,0.009866054,0.0009013016,0.00001100455],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008714495,"about_ca_system_score_gemma":0.0001915747,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001309729,"about_ca_topic_score_gemma":0.00001777302,"domain_scores_codex":[0.9978243,0.0001120471,0.000556255,0.0004879942,0.0004996854,0.0005196917],"domain_scores_gemma":[0.996734,0.0002445321,0.0006152211,0.001700524,0.0006261297,0.00007956645],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0007579907,0.001499231,0.02156007,0.0007341767,0.002109409,0.002121493,0.01423213,0.0006722389,0.08708673,0.005508283,0.7880887,0.07562959],"study_design_scores_gemma":[0.001838022,0.0006714952,0.0003205544,0.001128665,0.00004807143,0.002246236,0.0003255695,0.4388314,0.4794436,0.03069847,0.04392826,0.0005197034],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.221285,0.0004372196,0.7668378,0.009946217,0.000833018,0.0001036849,0.000002950161,0.0002478746,0.0003062437],"genre_scores_gemma":[0.5694113,0.00005111935,0.4296347,0.0003294568,0.0001105414,0.00000604587,0.000003682245,0.00002302747,0.0004301348],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7441604,"threshold_uncertainty_score":0.9981419,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02012211684514099,"score_gpt":0.2681842168796034,"score_spread":0.2480621000344624,"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."}}