{"id":"W3116637734","doi":"10.1109/tii.2020.3045161","title":"MAGLeak: A Learning-Based Side-Channel Attack for Password Recognition With Multiple Sensors in IIoT Environment","year":2020,"lang":"en","type":"article","venue":"IEEE Transactions on Industrial Informatics","topic":"User Authentication and Security Systems","field":"Computer Science","cited_by":52,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Windsor","funders":"National Natural Science Foundation of China","keywords":"Password; Side channel attack; Computer science; Keystroke logging; Accelerometer; Process (computing); Key (lock); Computer security; Channel (broadcasting); Gyroscope; Embedded system; Human–computer interaction; Artificial intelligence; Real-time computing; Engineering; Cryptography; Computer network","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005964561,0.0007179343,0.0008463895,0.0005282734,0.0003454032,0.0004671243,0.0008470982,0.0007465489,0.0009689531],"category_scores_gemma":[0.001636233,0.0002026796,0.0004308887,0.0002928419,0.000408365,0.001199643,0.001356267,0.0007979224,0.000655378],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002370275,"about_ca_system_score_gemma":0.0003778145,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006201849,"about_ca_topic_score_gemma":0.0009168085,"domain_scores_codex":[0.9993267,0.0001326512,0.00004339248,0.0001599339,0.0002236086,0.0001137489],"domain_scores_gemma":[0.9992691,0.0002166997,0.0001304944,0.000181986,0.0001298236,0.00007196517],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.002157779,0.0006271205,0.01726607,0.0003874064,0.0002681367,0.001247424,0.0002135474,0.06099636,0.1584176,0.003813758,0.009560482,0.7450442],"study_design_scores_gemma":[0.00004332203,0.0007981455,0.004923011,0.00001993949,0.00003867662,0.001219196,0.00005015304,0.9263064,0.06275743,0.001244122,0.002550817,0.00004885086],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1458879,0.0006866842,0.8436697,0.0002566913,0.0002270625,0.0001781768,0.0001930825,0.00720931,0.001691335],"genre_scores_gemma":[0.9222249,0.0001835151,0.07480107,0.0001845087,0.00003981284,0.00006619441,0.0002219563,0.00004932704,0.002228902],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.0009689531,"threshold_uncertainty_score":0.003241479,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09644512693821511,"score_gpt":0.2452915396314581,"score_spread":0.1488464126932429,"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."}}