{"id":"W4414002929","doi":"10.1007/978-3-031-94455-0_22","title":"Tarnhelm: Using Adversarial Samples to Protect User Privacy Against Traffic Identification","year":2025,"lang":"en","type":"book-chapter","venue":"Lecture notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering","topic":"Internet Traffic Analysis and Secure E-voting","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Queen's University","funders":"","keywords":"Adversarial system; Identification (biology); Computer security; Computer science; Internet privacy; Artificial intelligence; Biology","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":[0.0005227722,0.0003038834,0.0004176958,0.0003790966,0.000923873,0.0004292851,0.002652355,0.0002040314,5.94876e-7],"category_scores_gemma":[0.0001208648,0.0002561609,0.0002500306,0.0003979478,0.0001871383,0.000397576,0.001019681,0.0003773809,7.193008e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001175937,"about_ca_system_score_gemma":0.000302785,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001900895,"about_ca_topic_score_gemma":0.00005869629,"domain_scores_codex":[0.9983232,0.00001815751,0.0008434413,0.0002502234,0.0003071551,0.0002578492],"domain_scores_gemma":[0.9983951,0.0002198692,0.0005287576,0.000556571,0.0002468383,0.00005290808],"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":[0.000001244854,0.000008637423,2.90665e-7,0.00009225994,0.00008135476,5.013768e-8,0.001633563,0.9076103,0.00001771612,0.07233532,0.00006702931,0.01815221],"study_design_scores_gemma":[0.0001252887,0.00003188487,0.000006759174,0.0002996592,0.00005765875,0.000002700546,0.000004420162,0.9769459,0.00006458276,0.00006321906,0.02212945,0.0002684614],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001176788,0.000128919,0.9962043,0.0006111961,0.0006925574,0.0007698743,0.00003687245,0.00007972147,0.0002998229],"genre_scores_gemma":[0.1175112,0.00002451901,0.8819016,0.0002172422,0.0001695719,0.00002183113,0.00003361256,0.00001353627,0.0001068324],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.1163344,"threshold_uncertainty_score":0.999989,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02704136408265294,"score_gpt":0.2515902280302142,"score_spread":0.2245488639475613,"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."}}