{"id":"W4313023659","doi":"10.1109/jsyst.2022.3223694","title":"Active Learning Based Adversary Evasion Attacks Defense for Malwares in the Internet of Things","year":2022,"lang":"en","type":"article","venue":"IEEE Systems Journal","topic":"Advanced Malware Detection Techniques","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"Brandon University","funders":"","keywords":"Computer science; Malware; Adversary; Adversarial system; Android malware; Evasion (ethics); Feature selection; Android (operating system); Computer security; Machine learning; The Internet; Classifier (UML); Artificial intelligence; World Wide Web; Operating system","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":[],"consensus_categories":[],"category_scores_codex":[0.00174158,0.0001073556,0.0001823379,0.0002765267,0.0002621241,0.00007244252,0.0008536292,0.00003703311,0.000007040872],"category_scores_gemma":[0.0001170771,0.00008424789,0.0001156337,0.0003034125,0.00002316651,0.0005102227,0.0001011491,0.0006681508,8.554229e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002726594,"about_ca_system_score_gemma":0.0001197438,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006040527,"about_ca_topic_score_gemma":0.000002003711,"domain_scores_codex":[0.9981648,0.0006056122,0.0003774923,0.0001959468,0.0004566004,0.000199511],"domain_scores_gemma":[0.998714,0.0004090837,0.0004820245,0.000222266,0.000137243,0.00003532529],"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":[0.0009830026,0.0004070713,0.002886641,0.0003637499,0.0001250269,0.000400723,0.0469192,0.8509265,0.02342497,0.00190392,0.008431745,0.06322747],"study_design_scores_gemma":[0.003076964,0.003756084,0.0009078039,0.0006292282,0.00003237807,0.00266664,0.007671616,0.8765455,0.05374274,0.003680791,0.04659132,0.0006989685],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04071796,0.0001238333,0.9575135,0.0001492693,0.0008958045,0.0003840978,0.000002635251,0.00007916336,0.000133794],"genre_scores_gemma":[0.9925249,0.000003562162,0.007028798,0.0001441761,0.00006270086,0.0001118913,7.675923e-7,0.00001150258,0.0001117566],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9518069,"threshold_uncertainty_score":0.3435529,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02129753232483547,"score_gpt":0.2737181880002327,"score_spread":0.2524206556753973,"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."}}