{"id":"W4392980148","doi":"10.1109/tsc.2024.3377931","title":"Efficient and Privacy-Preserving Federated Learning Against Poisoning Adversaries","year":2024,"lang":"en","type":"article","venue":"IEEE Transactions on Services Computing","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of New Brunswick","funders":"Fundamental Research Funds for the Central Universities; National Natural Science Foundation of China; Higher Education Discipline Innovation Project; Ant Group","keywords":"Computer science; Upload; Federated learning; Computer security; Overhead (engineering); Confidentiality; Scale (ratio); Artificial intelligence; Machine learning; World Wide Web","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":["metaepi_narrow","scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.0006115312,0.0003888226,0.0003102477,0.0005174309,0.001260021,0.001785101,0.007730184,0.0001888551,0.00001018467],"category_scores_gemma":[0.000238522,0.0003921405,0.0001015577,0.001352021,0.00009345123,0.0006962209,0.002623487,0.001107758,0.00005770792],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001390494,"about_ca_system_score_gemma":0.00007253655,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001076389,"about_ca_topic_score_gemma":0.00002907278,"domain_scores_codex":[0.9971296,0.0001585622,0.0004636766,0.001113459,0.000467836,0.0006668511],"domain_scores_gemma":[0.996567,0.000731718,0.0001178359,0.002359051,0.00009579239,0.0001286336],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002530592,0.0001360921,0.0001766574,0.001095096,0.0002744199,0.0001894189,0.004589612,0.4979637,0.00589622,0.0005411959,0.0005422266,0.4885701],"study_design_scores_gemma":[0.0002306554,0.000066551,0.00009294243,0.0009891782,0.00001927234,0.00004059291,0.0004951099,0.9906424,0.005105902,0.001043261,0.0008777975,0.0003963142],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2386006,0.0005835667,0.7519534,0.003771038,0.0009445386,0.0001843562,0.000005824842,0.003609328,0.0003473249],"genre_scores_gemma":[0.9020706,0.0000691772,0.09748262,0.0002386151,0.00004859192,0.000009223501,0.000004400946,0.00004172934,0.0000349889],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.66347,"threshold_uncertainty_score":0.9998531,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01477667220527104,"score_gpt":0.254950718373431,"score_spread":0.2401740461681599,"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."}}