{"id":"W2170916850","doi":"10.1109/cisda.2011.5945941","title":"A Comparison of three machine learning techniques for encrypted network traffic analysis","year":2011,"lang":"en","type":"article","venue":"","topic":"Internet Traffic Analysis and Secure E-voting","field":"Computer Science","cited_by":56,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dalhousie University","funders":"","keywords":"Computer science; Robustness (evolution); Traffic classification; Encryption; Data mining; Artificial intelligence; TRACE (psycholinguistics); Machine learning; Cluster analysis; Payload (computing); Traffic generation model; Test data; Ground truth; Real-time computing; Computer network; Network packet","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":[0.003425495,0.001584511,0.001251089,0.004538065,0.0005963907,0.001330139,0.001496782,0.001440705,0.0009105474],"category_scores_gemma":[0.008428219,0.0003315181,0.001157241,0.00223515,0.0004238474,0.002008314,0.000851846,0.00132287,0.0005591894],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001111723,"about_ca_system_score_gemma":0.001269705,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005127201,"about_ca_topic_score_gemma":0.003605079,"domain_scores_codex":[0.9971321,0.0007583844,0.0002265916,0.0003621306,0.001256784,0.0002640317],"domain_scores_gemma":[0.9943501,0.003040322,0.0004006267,0.0004522743,0.001598704,0.0001579477],"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":[0.0008407416,0.0006581277,0.01232862,0.0003677397,0.0005003478,0.00009575166,0.0001240412,0.2620534,0.005681402,0.002766937,0.002434314,0.7121485],"study_design_scores_gemma":[0.00001838195,0.0001604381,0.003062972,0.00002823908,0.00003770278,0.00006528923,0.00005575113,0.9905475,0.004296556,0.0008833431,0.0008211628,0.00002264454],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2201897,0.004042732,0.7606403,0.0006373866,0.0003826992,0.0003394778,0.000446995,0.005843544,0.007477064],"genre_scores_gemma":[0.6700897,0.001193081,0.324735,0.0001539306,0.0001043605,0.000202773,0.0008884354,0.0001895398,0.002443276],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005127201,"threshold_uncertainty_score":0.01811594,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04112020147808059,"score_gpt":0.2825425469393867,"score_spread":0.2414223454613061,"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."}}