{"id":"W4402156097","doi":"10.1109/icc51166.2024.10622742","title":"Towards Well-trained Model Robustness in Federated Learning: An Adversarial- Example-Generation- Efficiency Perspective","year":2024,"lang":"en","type":"article","venue":"","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University","funders":"National Natural Science Foundation of China","keywords":"Adversarial system; Robustness (evolution); Computer science; Perspective (graphical); Artificial intelligence; Machine learning","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003888794,0.001213665,0.001224987,0.0005539855,0.000563235,0.001103545,0.001810439,0.001728385,0.001349682],"category_scores_gemma":[0.01178487,0.0005536046,0.0007699211,0.0003683194,0.001822503,0.002334827,0.002542452,0.002484474,0.0004278186],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009399031,"about_ca_system_score_gemma":0.001535211,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001919969,"about_ca_topic_score_gemma":0.001418996,"domain_scores_codex":[0.9986427,0.0005247244,0.00007350562,0.0003193785,0.0002586922,0.000180975],"domain_scores_gemma":[0.9960996,0.001924313,0.0003553049,0.0009304465,0.000507745,0.0001825602],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0001164869,0.00004667273,0.0008476181,0.00005214278,0.000047189,0.00007160237,0.00006194914,0.950568,0.00256907,0.01190976,0.0008277533,0.03288184],"study_design_scores_gemma":[0.000005134965,0.00002356508,0.0000488299,0.000004604252,0.000003898883,0.00001817452,0.000005282472,0.9934338,0.0009481865,0.005351471,0.0001535483,0.000003412485],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03760093,0.0002632475,0.9593096,0.0005002883,0.00003597781,0.00005242054,0.00004482518,0.0008099606,0.001382654],"genre_scores_gemma":[0.8627172,0.0001987718,0.1341063,0.0003725571,0.00004753642,0.0001292547,0.0001621787,0.0001927369,0.002073516],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003888794,"threshold_uncertainty_score":0.02056617,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03492455370878724,"score_gpt":0.3012251720324484,"score_spread":0.2663006183236612,"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."}}