{"id":"W4323349101","doi":"10.56553/popets-2023-0047","title":"DeepSE-WF: Unified Security Estimation for Website Fingerprinting Defenses","year":2023,"lang":"en","type":"article","venue":"Proceedings on Privacy Enhancing Technologies","topic":"Internet Traffic Analysis and Secure E-voting","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Fundação para a Ciência e a Tecnologia","keywords":"Computer science; Adversary; Computer security; Estimator; Bayes' theorem; Naive Bayes classifier; Machine learning; The Internet; Mutual information; Feature (linguistics); Artificial intelligence; Data mining; Bayesian probability; World Wide Web; Support vector machine; Mathematics; Statistics","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":[0.0009800281,0.0002964571,0.0003508312,0.0006573094,0.0004033993,0.0004668578,0.001623248,0.00022827,0.000001994863],"category_scores_gemma":[0.003551923,0.0002752212,0.0001701227,0.001441994,0.00006920641,0.0005969361,0.0008792646,0.0003689039,0.00009064538],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009790286,"about_ca_system_score_gemma":0.00003440586,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003264573,"about_ca_topic_score_gemma":0.000004666364,"domain_scores_codex":[0.9976816,0.000007892177,0.0004967147,0.0007905795,0.0003639678,0.0006592505],"domain_scores_gemma":[0.99872,0.0003266452,0.0003333114,0.0002849677,0.0002961151,0.00003895222],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001942582,0.00006096883,0.0003621216,0.0002644117,0.00007675085,0.000005981112,0.003991866,0.001771923,0.006136153,0.9171639,0.002300162,0.0678463],"study_design_scores_gemma":[0.0001977253,0.0001346349,0.00009212521,0.0002375985,0.00001910354,0.000006454401,0.001089889,0.8729719,0.108423,0.01557016,0.0009082187,0.0003491621],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5798817,0.00003707387,0.4101581,0.001826908,0.0001817595,0.0003168639,0.000001204573,0.007265081,0.0003313193],"genre_scores_gemma":[0.9332662,0.00002757213,0.06636577,0.00008273977,0.00004143074,0.0001115125,0.000004581339,0.00002572001,0.00007446957],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9015937,"threshold_uncertainty_score":0.99997,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01926564290623482,"score_gpt":0.2628370231901742,"score_spread":0.2435713802839393,"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."}}