{"id":"W3166964991","doi":"10.1109/iscc53001.2021.9631407","title":"Evaluating Resilience of Encrypted Traffic Classification against Adversarial Evasion Attacks","year":2021,"lang":"en","type":"article","venue":"2021 IEEE Symposium on Computers and Communications (ISCC)","topic":"Internet Traffic Analysis and Secure E-voting","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Artificial intelligence; Adversarial machine learning; Deep learning; Convolutional neural network; Machine learning; Adversarial system; Encryption; Evasion (ethics); Decision tree; Traffic classification; Resilience (materials science); Artificial neural network; The Internet; Computer security","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":[0.0007950494,0.0002392898,0.0003759151,0.0002029622,0.0004656541,0.0002345244,0.001745721,0.000123656,0.00001173949],"category_scores_gemma":[0.00007083519,0.0002388115,0.0001898656,0.0008336795,0.0001763576,0.0002992514,0.0005865774,0.0003575494,0.00001900648],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008026855,"about_ca_system_score_gemma":0.0002066227,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008053568,"about_ca_topic_score_gemma":0.00003469914,"domain_scores_codex":[0.9971453,0.000663999,0.0007279203,0.0006659222,0.0005131644,0.0002836921],"domain_scores_gemma":[0.9966595,0.0005980093,0.0003912434,0.001747666,0.0004890445,0.0001145836],"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":[0.00005316173,0.001169666,0.0001445849,0.00007713387,0.0002908277,0.0000183221,0.007612038,0.3752106,0.05813078,0.2079984,0.001881256,0.3474133],"study_design_scores_gemma":[0.0005150823,0.0001631291,0.0002748932,0.0002236822,0.00003988693,0.000009043278,0.0003009721,0.9961704,0.001318744,0.00001728548,0.0007276589,0.0002392135],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4851356,0.0007467942,0.503396,0.005141353,0.001138637,0.0003803323,0.00001057372,0.0001490954,0.003901612],"genre_scores_gemma":[0.9558834,0.0006003756,0.0429558,0.0002778623,0.00008993287,0.00001797217,0.00005158986,0.0000134012,0.0001096544],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6209598,"threshold_uncertainty_score":0.9738449,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04771848852167267,"score_gpt":0.3142296023966789,"score_spread":0.2665111138750062,"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."}}