{"id":"W2009255782","doi":"10.1007/s10922-014-9324-6","title":"How Robust Can a Machine Learning Approach Be for Classifying Encrypted VoIP?","year":2014,"lang":"en","type":"article","venue":"Journal of Network and Systems Management","topic":"Internet Traffic Analysis and Secure E-voting","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Computer science; Traffic classification; Deep packet inspection; Encryption; Voice over IP; Computer network; Traffic generation model; Firewall (physics); Network security; Internet traffic; Network packet; The Internet; Payload (computing); Quality of service; Traffic analysis; Computer security","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":[0.01959316,0.001749142,0.002584943,0.002783163,0.001024901,0.005941075,0.002440504,0.006004,0.001932868],"category_scores_gemma":[0.09767465,0.0006819437,0.001541664,0.00145942,0.003058574,0.00893719,0.001664306,0.004338273,0.002797615],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001133438,"about_ca_system_score_gemma":0.0009943357,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003393855,"about_ca_topic_score_gemma":0.001289576,"domain_scores_codex":[0.9915168,0.003294887,0.0007663253,0.0016366,0.002313535,0.0004719841],"domain_scores_gemma":[0.9595594,0.02491226,0.002412661,0.006311675,0.006187061,0.0006170352],"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":[0.0008953632,0.000497948,0.0526169,0.0003299189,0.001645647,0.0002297199,0.000209833,0.196698,0.007189,0.01801894,0.01472859,0.7069401],"study_design_scores_gemma":[0.00004456568,0.0001928399,0.00795126,0.0001461976,0.0001712654,0.0003189833,0.0003204093,0.9102209,0.007559828,0.06887171,0.004111311,0.00009068477],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1761389,0.005975338,0.7768937,0.0291757,0.001791394,0.0001831077,0.0009026535,0.002430918,0.006508261],"genre_scores_gemma":[0.9033493,0.001355022,0.08763682,0.002190063,0.001894811,0.0000946207,0.0005648695,0.0002038565,0.002710722],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01959316,"threshold_uncertainty_score":0.1036198,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0289963292342805,"score_gpt":0.2166735818630921,"score_spread":0.1876772526288116,"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."}}