{"id":"W4286257109","doi":"10.56553/popets-2022-0074","title":"Trace Oddity: Methodologies for Data-Driven Traffic Analysis on Tor","year":2022,"lang":"en","type":"article","venue":"Proceedings on Privacy Enhancing Technologies","topic":"Internet Traffic Analysis and Secure E-voting","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"York University; KU Leuven; New York University Abu Dhabi","keywords":"Computer science; Deep learning; Metadata; Data mining; TRACE (psycholinguistics); Artificial intelligence; Proxy (statistics); Web traffic; Traffic analysis; Machine learning; Real-time computing; Computer security; The Internet","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.002213984,0.0004130514,0.0007750359,0.001240818,0.0007698684,0.0003953898,0.007125189,0.0001686839,0.00002007014],"category_scores_gemma":[0.003147505,0.0003679019,0.0003674274,0.002567694,0.0001039245,0.0005765099,0.003388633,0.0007767613,0.00001140603],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002589971,"about_ca_system_score_gemma":0.00006009762,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003803065,"about_ca_topic_score_gemma":0.00001026583,"domain_scores_codex":[0.9961962,0.00005312133,0.0006432662,0.001662717,0.000721273,0.0007234619],"domain_scores_gemma":[0.997372,0.0008472832,0.00052037,0.001023323,0.0001880018,0.00004903645],"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":[0.000194588,0.0005623781,0.00009711001,0.0001471058,0.002149871,0.00002099712,0.004704834,0.1340002,0.001794412,0.467029,0.01669182,0.3726077],"study_design_scores_gemma":[0.0002842097,0.0007739071,0.00002363255,0.00002939144,0.0003067061,0.000007365813,0.003361579,0.9702237,0.009495541,0.000821945,0.01415062,0.0005213889],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3783777,0.0002065597,0.6096373,0.005539977,0.0003669948,0.0005929912,0.00003974915,0.005067513,0.0001712689],"genre_scores_gemma":[0.8236731,0.00002555553,0.1756391,0.0001874227,0.0000449346,0.0002641031,0.00002362796,0.00002488334,0.0001172836],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8362235,"threshold_uncertainty_score":0.9998773,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06947437076476866,"score_gpt":0.317711197390618,"score_spread":0.2482368266258494,"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."}}