{"id":"W4388832684","doi":"10.3390/info14110620","title":"Comparative Analysis of Membership Inference Attacks in Federated and Centralized Learning","year":2023,"lang":"en","type":"article","venue":"Information","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Manitoba; University of Windsor","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Federated learning; Inference; Machine learning; Information leakage; Artificial intelligence; Vulnerability (computing); Bayesian inference; Data mining; Computer security; Bayesian probability","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003645714,0.00006145793,0.0001766943,0.0006838948,0.00004625995,0.0001185477,0.001889303,0.00005391959,0.000007784013],"category_scores_gemma":[0.003687546,0.00005997829,0.00001818418,0.002997564,0.00003740844,0.001923379,0.00509477,0.0001256061,0.00001945549],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003004843,"about_ca_system_score_gemma":0.00002167075,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001064919,"about_ca_topic_score_gemma":0.00005289831,"domain_scores_codex":[0.9992812,0.00005237885,0.0002757989,0.00009159181,0.0001582098,0.0001408072],"domain_scores_gemma":[0.9989086,0.0001938616,0.0001540929,0.0006558301,0.00006903941,0.00001852539],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001205262,0.0001029424,0.5937106,0.0003684443,0.001251938,0.00001469317,0.06939007,0.131685,0.001954924,0.04198556,0.03457889,0.1248365],"study_design_scores_gemma":[0.0001701977,0.00001371876,0.08621353,0.00001486032,0.000009290929,2.315083e-7,0.0003708121,0.9080336,0.001189406,0.003783083,0.0001398465,0.00006144157],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9270533,0.0000108988,0.0693742,0.00133247,0.00004492274,0.0001242018,0.000007849807,0.0004647502,0.001587441],"genre_scores_gemma":[0.9930665,0.00002945944,0.006774713,0.00002261037,8.39933e-7,0.000005926566,0.00009476,7.039209e-7,0.000004451065],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7763487,"threshold_uncertainty_score":0.6350266,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06122179476991954,"score_gpt":0.3355503844406063,"score_spread":0.2743285896706867,"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."}}