{"id":"W4313887286","doi":"10.1109/jstsp.2023.3235302","title":"EyeDrive: A Deep Learning Model for Continuous Driver Authentication","year":2023,"lang":"en","type":"article","venue":"IEEE Journal of Selected Topics in Signal Processing","topic":"Gaze Tracking and Assistive Technology","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Biometrics; Authentication (law); Modality (human–computer interaction); Context (archaeology); Artificial intelligence; Deep learning; Frame (networking); Frame rate; Focus (optics); Identification (biology); Computer vision; Machine learning; Computer security; 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004621469,0.0001025179,0.0002164399,0.0004187296,0.000135958,0.0001032311,0.0004704176,0.0001026489,9.296974e-7],"category_scores_gemma":[0.0001561261,0.00009571164,0.00005269024,0.0009942305,0.00004172412,0.0003548291,0.00003192774,0.000436517,0.000002401081],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006930454,"about_ca_system_score_gemma":0.0001632155,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":8.075404e-7,"about_ca_topic_score_gemma":0.000002614952,"domain_scores_codex":[0.9988852,0.0000443116,0.0003970676,0.0001797065,0.0002149442,0.0002788036],"domain_scores_gemma":[0.998793,0.0001016304,0.0003654913,0.00007926034,0.0006185705,0.00004206673],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00005196206,0.0001750903,0.00795433,0.0001394065,0.00004947256,0.00008011088,0.006117173,0.09083892,0.092381,0.003354763,0.0002296462,0.7986282],"study_design_scores_gemma":[0.0004721142,0.0001300235,0.00355194,0.0001188094,0.0000118506,0.0000347527,0.00005907456,0.9779252,0.004509939,0.01296631,0.0001102015,0.0001097647],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2614325,0.00008531163,0.7377396,0.0004702889,0.0000823093,0.00005875416,1.731429e-7,0.000103894,0.00002710961],"genre_scores_gemma":[0.9578164,0.00001510099,0.04178711,0.00003020324,0.0001124086,0.000005565867,7.2376e-7,0.00001005205,0.0002224081],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8870863,"threshold_uncertainty_score":0.3903008,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02298817860612179,"score_gpt":0.2870810671956061,"score_spread":0.2640928885894843,"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."}}