{"id":"W2064446036","doi":"10.1016/j.jksuci.2014.03.013","title":"Identification of VoIP encrypted traffic using a machine learning approach","year":2015,"lang":"en","type":"article","venue":"Journal of King Saud University - Computer and Information Sciences","topic":"Internet Traffic Analysis and Secure E-voting","field":"Computer Science","cited_by":54,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dalhousie University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Payload (computing); Voice over IP; Computer science; AdaBoost; Encryption; Traffic classification; Machine learning; Deep packet inspection; Identification (biology); Artificial intelligence; Set (abstract data type); Genetic programming; Feature (linguistics); Network packet; Data mining; Computer network; The Internet; Support vector machine; Operating system","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00156374,0.00006920553,0.0001661629,0.0005330769,0.0001900032,0.0002290595,0.000527026,0.00003199016,8.701231e-7],"category_scores_gemma":[0.00003606807,0.00005871212,0.000068287,0.0006227418,0.00009702683,0.004446412,0.0001155911,0.0001312032,7.324337e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000430501,"about_ca_system_score_gemma":0.0001202601,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001713504,"about_ca_topic_score_gemma":0.000001644819,"domain_scores_codex":[0.9988548,0.00009049057,0.0004241014,0.00008501457,0.000441941,0.0001036126],"domain_scores_gemma":[0.9986034,0.00003966257,0.0008217432,0.00004924318,0.000410767,0.00007518381],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001249907,0.00003298719,0.0008072698,0.00002178316,0.00003478269,0.000002530433,0.0141089,0.9357822,0.00006263407,0.02794734,0.00004077755,0.02114628],"study_design_scores_gemma":[0.0002616726,0.0001190043,0.0003500656,0.00002837276,0.00001411507,0.00007250178,0.001092447,0.9972413,0.00003206068,0.000008040418,0.0007160756,0.0000643085],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3616534,0.00002935836,0.6380137,0.00004114246,0.0001125038,0.00001886325,2.884397e-7,0.00000946838,0.0001212101],"genre_scores_gemma":[0.9581103,0.00001318991,0.04180794,0.00002995106,0.0000302993,9.701786e-9,7.399109e-7,7.880573e-7,0.00000682252],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5964568,"threshold_uncertainty_score":0.3223541,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02532095127815772,"score_gpt":0.2281666592521639,"score_spread":0.2028457079740062,"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."}}