{"id":"W4292387419","doi":"10.1109/access.2022.3200034","title":"Network Intrusion Detection via Flow-to-Image Conversion and Vision Transformer Classification","year":2022,"lang":"en","type":"article","venue":"IEEE Access","topic":"Network Security and Intrusion Detection","field":"Computer Science","cited_by":55,"is_retracted":false,"has_abstract":true,"ca_institutions":"Ericsson (Canada); University of Regina","funders":"Mitacs","keywords":"Computer science; Artificial intelligence; Contextual image classification; Intrusion detection system; Decision tree; Pattern recognition (psychology); Deep learning; Classifier (UML); Binary classification; Machine learning; Data mining; Image (mathematics); Support vector machine","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004730048,0.0008553137,0.000753411,0.002459466,0.0002545289,0.0007890133,0.000908176,0.0005372264,0.001170557],"category_scores_gemma":[0.001242299,0.0002310551,0.0007965007,0.00113046,0.0004753529,0.001498251,0.0007321383,0.0008399344,0.0005023082],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006881725,"about_ca_system_score_gemma":0.0005234929,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003457274,"about_ca_topic_score_gemma":0.002593826,"domain_scores_codex":[0.9994984,0.00004508676,0.00002599114,0.0001331293,0.0002018716,0.00009553682],"domain_scores_gemma":[0.9996738,0.00005938254,0.00005779447,0.00005598694,0.0001264077,0.00002650499],"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":[0.000312128,0.000366614,0.007522216,0.00009228825,0.00008348338,0.0001640979,0.00006550011,0.02901565,0.03966748,0.003415213,0.004385329,0.91491],"study_design_scores_gemma":[0.00001632217,0.0001204971,0.005210258,0.00001249266,0.00003807346,0.000324516,0.00003203191,0.9417758,0.04705415,0.003009957,0.002384611,0.00002124461],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1584788,0.0006480523,0.829784,0.0002992995,0.0001683094,0.0002182375,0.0003567255,0.005979782,0.004066888],"genre_scores_gemma":[0.7990955,0.0005070897,0.1958024,0.0001623153,0.00006915237,0.0001141695,0.0009231513,0.0001052953,0.003220941],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003457274,"threshold_uncertainty_score":0.006874323,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0171855981660338,"score_gpt":0.2714975083848661,"score_spread":0.2543119102188323,"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."}}