{"id":"W4399358245","doi":"10.1016/j.cose.2024.103936","title":"FedIMP: Parameter Importance-based Model Poisoning attack against Federated learning system","year":2024,"lang":"en","type":"article","venue":"Computers & Security","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":false,"ca_institutions":"Brock University","funders":"National Natural Science Foundation of China","keywords":"Computer science; Boosting (machine learning); Federated learning; Vulnerability (computing); Convergence (economics); Similarity (geometry); Computer security; Machine learning; 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":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0009166175,0.000510347,0.0005263361,0.0002885967,0.0006821595,0.001685373,0.001257215,0.0002233418,0.000006555145],"category_scores_gemma":[0.0001469809,0.0005075656,0.0002778082,0.0009301854,0.00009158099,0.001013542,0.0006535642,0.001427095,0.00009292089],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004757188,"about_ca_system_score_gemma":0.0003353559,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002123535,"about_ca_topic_score_gemma":0.00001186601,"domain_scores_codex":[0.9962472,0.000386039,0.0006345897,0.001279524,0.0006334654,0.0008192004],"domain_scores_gemma":[0.9980494,0.0006417007,0.0002154721,0.000681559,0.0001459982,0.0002658629],"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":[0.00001261345,0.00003080926,0.0008253053,0.0002886266,0.00006440798,0.0003668844,0.001298836,0.9784727,0.00005494776,0.007343075,0.001802163,0.009439609],"study_design_scores_gemma":[0.0004383841,0.00006473857,0.0000759987,0.0005330215,0.00002077547,0.00003241972,0.00006961669,0.9959077,0.0000641103,0.0003260914,0.001899551,0.0005676241],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1022855,0.0005272841,0.8899059,0.0007443438,0.002103013,0.0002805983,0.000003079078,0.003023391,0.001126842],"genre_scores_gemma":[0.9228103,0.000005777682,0.07618301,0.0005228834,0.0003014869,0.00002263408,0.00003359889,0.00006337364,0.00005690208],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8205248,"threshold_uncertainty_score":0.9997376,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01843278694387394,"score_gpt":0.2659551696673857,"score_spread":0.2475223827235118,"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."}}