{"id":"W3003395041","doi":"10.1109/iscc47284.2019.8969578","title":"Integrating Machine Learning with Off-the-Shelf Traffic Flow Features for HTTP/HTTPS Traffic Classification","year":2019,"lang":"en","type":"article","venue":"","topic":"Internet Traffic Analysis and Secure E-voting","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dalhousie University","funders":"","keywords":"Traffic classification; Computer science; Header; Traffic generation model; Encryption; Robustness (evolution); The Internet; Machine learning; Leverage (statistics); Key (lock); Deep packet inspection; Support vector machine; Data mining; Artificial intelligence; Computer network; Network packet; Computer security; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001912625,0.001432959,0.0009556131,0.002858367,0.0004350292,0.0009557169,0.001144924,0.00121903,0.001413679],"category_scores_gemma":[0.004048101,0.0002770392,0.0006796978,0.00129303,0.0003273405,0.00163736,0.0007546519,0.001279428,0.001434893],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006789591,"about_ca_system_score_gemma":0.0006844896,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004398064,"about_ca_topic_score_gemma":0.003610537,"domain_scores_codex":[0.9990865,0.0002368456,0.00007862767,0.000216448,0.0002300075,0.0001516694],"domain_scores_gemma":[0.9978569,0.0008958313,0.0001674588,0.0003782021,0.0006172782,0.00008431936],"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":[0.0004080289,0.001790618,0.01991479,0.00008093211,0.0001601522,0.0001536033,0.00006126135,0.2287316,0.0222121,0.0007973096,0.005405579,0.7202839],"study_design_scores_gemma":[0.000006089216,0.0000617925,0.001266328,0.000003899473,0.000009993578,0.00001937512,0.000009878637,0.9915928,0.00631729,0.0003590944,0.0003452058,0.000008397574],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4711893,0.0004406383,0.503244,0.0003929693,0.0003229355,0.0003337024,0.0008817902,0.01949822,0.003696471],"genre_scores_gemma":[0.8836133,0.00008453686,0.1121063,0.0001003423,0.00008376275,0.0001446678,0.001863305,0.0001665596,0.001837201],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004398064,"threshold_uncertainty_score":0.01011503,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01146598110680701,"score_gpt":0.2271897064990406,"score_spread":0.2157237253922335,"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."}}