{"id":"W4391341820","doi":"10.1109/jiot.2024.3360007","title":"PA-iMFL: Communication-Efficient Privacy Amplification Method Against Data Reconstruction Attack in Improved Multilayer Federated Learning","year":2024,"lang":"en","type":"article","venue":"IEEE Internet of Things Journal","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University","funders":"Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"Computer science; Layer (electronics); Computer network; Information privacy; Computer security","routes":{"ca_aff":true,"ca_fund":true,"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":[0.002529283,0.0005708343,0.000700089,0.0006706879,0.0006985512,0.0009996054,0.001520447,0.001081145,0.001332527],"category_scores_gemma":[0.007135022,0.0002336786,0.0006285015,0.000588771,0.0009914997,0.003228894,0.002627932,0.001517089,0.0003778952],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000742453,"about_ca_system_score_gemma":0.001114596,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001119734,"about_ca_topic_score_gemma":0.001075614,"domain_scores_codex":[0.9982885,0.0005008627,0.0001184943,0.0003086149,0.0005138662,0.0002696551],"domain_scores_gemma":[0.9977031,0.0007809079,0.0002398245,0.0007719241,0.0003910697,0.0001131902],"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":[0.001037965,0.0003424035,0.005799674,0.0002029583,0.0001262019,0.0005039286,0.0006435738,0.2674946,0.02722067,0.03520482,0.006167165,0.6552561],"study_design_scores_gemma":[0.00003054829,0.0001580448,0.0004538925,0.00001452601,0.00001914254,0.0002242118,0.00005632962,0.9760233,0.009946188,0.01174708,0.001306754,0.00001996115],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03283666,0.0001708463,0.9642576,0.0002967797,0.0000257744,0.00004643523,0.00005609647,0.001303192,0.001006686],"genre_scores_gemma":[0.887023,0.0001134952,0.1102105,0.0003688323,0.00004216025,0.00008136737,0.0001507352,0.00005094103,0.001958894],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002529283,"threshold_uncertainty_score":0.01337624,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07139179133780606,"score_gpt":0.3521007656481742,"score_spread":0.2807089743103681,"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."}}