{"id":"W4385236985","doi":"10.1109/jiot.2023.3298663","title":"A GNN-Based Adversarial Internet of Things Malware Detection Framework for Critical Infrastructure: Studying Gafgyt, Mirai, and Tsunami Campaigns","year":2023,"lang":"en","type":"article","venue":"IEEE Internet of Things Journal","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":23,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary; Brandon University; University of Guelph","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Adversarial system; Malware; Computer science; Artificial intelligence; Machine learning; Detector; Classifier (UML); Data mining; Computer security","routes":{"ca_aff":true,"ca_fund":true,"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"],"consensus_categories":[],"category_scores_codex":[0.001750628,0.00033502,0.0005744658,0.0005716961,0.0001831262,0.0003152673,0.001364,0.00030027,0.00003999173],"category_scores_gemma":[0.00356346,0.0003155808,0.0002895611,0.0004953975,0.0002465275,0.001295378,0.000426932,0.001411272,0.000003658969],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001495998,"about_ca_system_score_gemma":0.0001343472,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001222792,"about_ca_topic_score_gemma":0.000003810614,"domain_scores_codex":[0.9970283,0.0002649396,0.000920077,0.0005174702,0.0007332887,0.0005359293],"domain_scores_gemma":[0.9964389,0.001809274,0.0007780904,0.0003533406,0.0004203375,0.0002000923],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00706953,0.0009946935,0.03819178,0.004520449,0.002807109,0.0009444652,0.2816018,0.1479958,0.09143025,0.09443054,0.008132434,0.3218811],"study_design_scores_gemma":[0.001610007,0.000929999,0.00116541,0.001114532,0.00009826486,0.0002297765,0.0008208866,0.9331445,0.01960778,0.04067893,0.0001867599,0.000413167],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1790614,0.00003853476,0.8167951,0.0004123769,0.003305157,0.0002123548,0.000002874069,0.0001345476,0.00003768696],"genre_scores_gemma":[0.8009585,0.000004163711,0.1983533,0.0002885529,0.0003062694,0.000009154784,0.000001515635,0.00003585999,0.00004270506],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7851486,"threshold_uncertainty_score":0.9999296,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02085065260052788,"score_gpt":0.3008743243671623,"score_spread":0.2800236717666344,"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."}}