{"id":"W3136919568","doi":"10.1109/ccnc49032.2021.9369591","title":"Unsupervised ML Based Detection of Malicious Web Sessions with Automated Feature Selection: Design and Real-World Validation","year":2021,"lang":"en","type":"article","venue":"","topic":"Network Security and Intrusion Detection","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"U.S. Nuclear Regulatory Commission","keywords":"Computer science; Feature selection; Session (web analytics); Preprocessor; Machine learning; Boosting (machine learning); Data mining; Feature extraction; Task (project management); Artificial intelligence; World Wide Web; Engineering","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":[0.0002406546,0.0001383885,0.0001657214,0.0001972138,0.000259113,0.0001205534,0.0001218725,0.0001056721,0.00006578039],"category_scores_gemma":[0.0000201008,0.0001151492,0.00003437101,0.001852779,0.00003216028,0.0004200114,0.00005106682,0.0001560818,0.000003395517],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000492445,"about_ca_system_score_gemma":0.0001859603,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001023641,"about_ca_topic_score_gemma":0.000566251,"domain_scores_codex":[0.998725,0.0002937381,0.0001873533,0.0003719964,0.0002521928,0.0001697436],"domain_scores_gemma":[0.9991046,0.0001254806,0.0001038729,0.0002723116,0.0003136249,0.00008007016],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003855747,0.0004697036,0.002665347,0.0001780036,0.0001326269,0.00005181987,0.0005597169,0.04872167,0.8804757,0.00704304,0.004877013,0.05443978],"study_design_scores_gemma":[0.0004253956,0.0001769648,0.002344316,0.0000424935,0.00001422369,0.00004371263,0.00001057062,0.6498477,0.3462393,0.0001132458,0.0006311452,0.0001108388],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.139884,0.00004575116,0.8571494,0.0008049054,0.0002018287,0.0002490395,0.0000011122,0.0009313739,0.0007326072],"genre_scores_gemma":[0.9280534,0.0000504612,0.07117954,0.0001678185,0.00004244004,0.00001823843,0.000006017473,0.00001041484,0.0004716773],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7881694,"threshold_uncertainty_score":0.4695648,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01340970372181609,"score_gpt":0.2372768681654132,"score_spread":0.2238671644435971,"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."}}