{"id":"W4226510616","doi":"10.1109/tii.2022.3167672","title":"IIoT Deep Malware Threat Hunting: From Adversarial Example Detection to Adversarial Scenario Detection","year":2022,"lang":"en","type":"article","venue":"IEEE Transactions on Industrial Informatics","topic":"Advanced Malware Detection Techniques","field":"Computer Science","cited_by":34,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary; University of Guelph","funders":"","keywords":"Computer science; Malware; Adversarial system; Artificial intelligence; Machine learning; Deep learning; Classifier (UML); Convolutional neural network; Leverage (statistics); Botnet; Data mining; Computer security; The Internet; 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","sts"],"consensus_categories":[],"category_scores_codex":[0.0005487065,0.0004434705,0.0004181564,0.0008664386,0.001745488,0.0003047785,0.00106349,0.0003658676,0.0002737573],"category_scores_gemma":[0.00006393033,0.0005232749,0.0002624031,0.001799013,0.00005617319,0.00182924,0.00006544498,0.001662188,0.0001181355],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00128039,"about_ca_system_score_gemma":0.0001990991,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002230899,"about_ca_topic_score_gemma":0.0007154802,"domain_scores_codex":[0.9965543,0.000215868,0.00107288,0.000525502,0.001018567,0.0006128456],"domain_scores_gemma":[0.9977761,0.0003027384,0.0004557937,0.001004241,0.0001778919,0.0002832612],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0009895302,0.0002432242,0.00000833755,0.00001111036,0.0001232949,0.000008843876,0.004133689,0.3037962,0.004929461,0.00009888321,0.0002124217,0.685445],"study_design_scores_gemma":[0.005483844,0.003261983,0.00003373165,0.00005027009,0.0001494627,0.0000998263,0.002779454,0.1990906,0.7371724,0.001364869,0.04900607,0.001507437],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02847301,0.000003254315,0.9593515,0.0001145474,0.009010306,0.001171266,0.0001067238,0.001476653,0.0002926684],"genre_scores_gemma":[0.9723989,0.000004880163,0.02592226,0.0004425426,0.0005452085,0.0004990502,0.00001514233,0.00004724799,0.0001248187],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9439259,"threshold_uncertainty_score":0.9997219,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03662857028806884,"score_gpt":0.2430309150710183,"score_spread":0.2064023447829494,"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."}}