{"id":"W4390262813","doi":"10.1007/s11227-023-05846-4","title":"Exploring privacy measurement in federated learning","year":2023,"lang":"en","type":"article","venue":"The Journal of Supercomputing","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":49,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Guelph","funders":"","keywords":"Computer science; Confidentiality; Information privacy; Privacy by Design; Field (mathematics); Data science; Computer security; Artificial intelligence","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":["metaresearch","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.007300109,0.000133098,0.0002240565,0.0004252024,0.0002819769,0.0001747514,0.01352752,0.00004045516,0.000002055542],"category_scores_gemma":[0.0178188,0.00009601672,0.00005682505,0.001577677,0.00003889934,0.001255276,0.02597179,0.0008800083,0.00002819094],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001944731,"about_ca_system_score_gemma":0.0000903392,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003793753,"about_ca_topic_score_gemma":0.000004745213,"domain_scores_codex":[0.9977434,0.0003282697,0.000577721,0.0001706994,0.0007503893,0.0004295239],"domain_scores_gemma":[0.9976974,0.0004352344,0.0002079073,0.001408836,0.0002027667,0.00004788816],"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":[0.00007891381,0.0002239467,0.03738287,0.0001546421,0.0002641969,0.0009601366,0.01909828,0.068315,0.07857175,0.001028669,0.03487683,0.7590448],"study_design_scores_gemma":[0.001001886,0.0002262605,0.03576725,0.0009410234,0.00001480213,0.0003732127,0.002951166,0.9235286,0.01407631,0.019211,0.001514786,0.000393673],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8863657,0.000183716,0.0986413,0.01378002,0.0004891492,0.00007598717,1.187114e-7,0.0003732302,0.00009080915],"genre_scores_gemma":[0.9759048,0.0002280459,0.02371596,0.00004273713,0.00009149993,0.000001328785,2.851302e-7,0.00001267972,0.000002666528],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8552136,"threshold_uncertainty_score":0.9918098,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.215619421984535,"score_gpt":0.2934067596087868,"score_spread":0.0777873376242518,"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."}}