{"id":"W4415293244","doi":"10.1109/access.2025.3622960","title":"Advancing Multi-Modal Behavioral Biometric Authentication: A Deep Learning Approach With Synthetic Data Generation","year":2025,"lang":"en","type":"article","venue":"IEEE Access","topic":"User Authentication and Security Systems","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Biometrics; Benchmark (surveying); Authentication (law); Deep learning; Synthetic data; Pairwise comparison; Differential privacy; Data modeling","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":[0.0004954399,0.0001526005,0.0001777158,0.0005753589,0.0002856246,0.0009516082,0.002493882,0.00006518935,0.000007343565],"category_scores_gemma":[0.00006165017,0.0001345571,0.00002874845,0.002170055,0.00004595027,0.00181414,0.0004161076,0.000162742,0.00002216146],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006345919,"about_ca_system_score_gemma":0.00009324417,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009506893,"about_ca_topic_score_gemma":0.00006280686,"domain_scores_codex":[0.9982291,0.000143282,0.0003040649,0.0007310823,0.0003286283,0.0002638075],"domain_scores_gemma":[0.9981373,0.00004950233,0.0001472008,0.001415319,0.0001715605,0.00007911147],"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":[0.0001010953,0.009609736,0.1143531,0.001555432,0.0007854819,0.00008551432,0.1291025,0.009362964,0.0487631,0.0319422,0.003891217,0.6504477],"study_design_scores_gemma":[0.0003560247,0.00002455889,0.002385026,0.0000283474,0.00003479232,0.00001094626,0.00008159854,0.9947791,0.001202643,0.00003447481,0.0008909122,0.0001715587],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.116095,0.0001864198,0.8823362,0.0002297574,0.0004531379,0.0003158257,0.000002701835,0.000193674,0.0001873158],"genre_scores_gemma":[0.9798262,0.000008860982,0.01953775,0.00007940717,0.00005935548,0.00006088231,0.00006139799,0.00001085444,0.0003553681],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9854162,"threshold_uncertainty_score":0.917638,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08470610970186984,"score_gpt":0.3592407229239627,"score_spread":0.2745346132220928,"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."}}