{"id":"W3164510030","doi":"10.1109/access.2021.3083421","title":"Security Hardening of Botnet Detectors Using Generative Adversarial Networks","year":2021,"lang":"en","type":"article","venue":"IEEE Access","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":36,"is_retracted":false,"has_abstract":true,"ca_institutions":"St. Francis Xavier University","funders":"Engineering and Physical Sciences Research Council; Northumbria University","keywords":"Botnet; Computer science; Adversarial system; Artificial intelligence; Machine learning; Malware; Emulation; Test set; Classifier (UML); Oversampling; Data mining; Computer security; Computer network; The Internet; Bandwidth (computing); 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002846719,0.001227589,0.001128042,0.001034052,0.0004003345,0.0008485367,0.001151221,0.001046205,0.001093082],"category_scores_gemma":[0.008770441,0.0004984073,0.0009494781,0.0003930732,0.001215706,0.001652476,0.001768425,0.00216226,0.0004219772],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001226,"about_ca_system_score_gemma":0.000753177,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001908436,"about_ca_topic_score_gemma":0.001943998,"domain_scores_codex":[0.9988298,0.0004225725,0.0000516405,0.0002574562,0.0002918926,0.0001466465],"domain_scores_gemma":[0.9951292,0.00305385,0.0004500255,0.0008090237,0.0004311572,0.0001265506],"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":[0.000103133,0.0000960356,0.00291805,0.00006057449,0.00007715043,0.00008217697,0.00005706827,0.9241893,0.006922679,0.004368407,0.001893594,0.05923183],"study_design_scores_gemma":[0.000003314954,0.00002370229,0.0001976215,0.000004919509,0.000004588881,0.00002437165,0.000004015906,0.9956642,0.00232613,0.001558998,0.0001835219,0.000004529605],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1960249,0.0006866813,0.7928541,0.0007552594,0.0001379899,0.0001675582,0.000215275,0.005322962,0.003835251],"genre_scores_gemma":[0.9315053,0.0001485435,0.06612293,0.0003183019,0.00004644913,0.00006185888,0.0003355461,0.000165214,0.001295867],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002846719,"threshold_uncertainty_score":0.01505506,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0323627462343424,"score_gpt":0.3187290371346199,"score_spread":0.2863662909002775,"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."}}