{"id":"W4390142817","doi":"10.1007/s12083-023-01597-4","title":"Unveiling DoH tunnel: Toward generating a balanced DoH encrypted traffic dataset and profiling malicious behavior using inherently interpretable machine learning","year":2023,"lang":"en","type":"article","venue":"Peer-to-Peer Networking and Applications","topic":"Internet Traffic Analysis and Secure E-voting","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":false,"ca_institutions":"York University","funders":"","keywords":"Overfitting; Interpretability; Computer science; Profiling (computer programming); Random forest; Data mining; Machine learning; Encryption; Artificial intelligence; The Internet; Artificial neural network; 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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001086567,0.000329969,0.0004019169,0.000298793,0.0007752416,0.0007462856,0.0005574221,0.000103545,0.000007625506],"category_scores_gemma":[0.00006756803,0.0003307978,0.00007271452,0.001404064,0.0000411248,0.0002043187,0.0005769016,0.0004622487,0.00003240173],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005705547,"about_ca_system_score_gemma":0.00004043426,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007944268,"about_ca_topic_score_gemma":0.00006789099,"domain_scores_codex":[0.9972079,0.0001054001,0.0005702259,0.000972954,0.0004691122,0.0006744076],"domain_scores_gemma":[0.9988263,0.0001571354,0.0001800983,0.0003451442,0.000202364,0.0002890161],"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":[0.00001272243,0.00008146296,0.002202751,0.00006276661,0.000101117,0.00002195244,0.004893973,0.8783023,0.00596714,0.003163421,0.001312649,0.1038777],"study_design_scores_gemma":[0.0002072973,0.00004510222,0.0001441124,0.0001012216,0.00006979183,0.00003268166,0.0003069202,0.9839767,0.00009141224,0.000007727624,0.01463943,0.0003776503],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4416198,0.0002612061,0.5561324,0.000596316,0.0001781921,0.0006288223,0.00006914157,0.0004739494,0.00004012651],"genre_scores_gemma":[0.9618881,0.00002161969,0.03607202,0.0002871495,0.0004780502,0.0002910931,0.0006708386,0.00004149855,0.0002496434],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5202683,"threshold_uncertainty_score":0.9999144,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03281763495495147,"score_gpt":0.293704309409292,"score_spread":0.2608866744543405,"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."}}