Behavioral embedding for continuous user verification in global settings

Levi, Matan; Hazan, Itay; Agmon, Noga; Eden, Sagi

doi:10.1016/j.cose.2022.102716

Cited by 2 publications

(3 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Researchers of [28][29][30] chose other ML classifiers for their models. In study [28], a continuous touch-dynamics authentication method was studied.…”

Section: Literature Reviewmentioning

confidence: 99%

“…RF, KNN, gradient boosting classifier (GBC), and linear SVM (L-SVM) classifiers were evaluated with these data. While RF and GBC had similar accuracy, GBC was chosen as the optimal classifier due to a faster performance with an average accuracy under the ROC curve (AUC) of 0.9692 and a learning time of 117 s. For [29], researchers attempted to create a privacy-preserving global continuous authentication model using touch dynamics. To achieve this, base features would be extracted from initial user sessions.…”

Section: Literature Reviewmentioning

confidence: 99%

“…[23] SVM 2.9% AER [24] SVM 97.7% ACC [25] RF 0.002 ± 0.000 EER [26] RF 91.79% TAR [27] RF >0.1% EER [28] GBC 0.9692 AUC [29] L-GBC 0.913-0.921% AUC […”

Section: Other Physiological Dynamicsmentioning

confidence: 99%

See 2 more Smart Citations

Deep Learning and Machine Learning, Better Together Than Apart: A Review on Biometrics Mobile Authentication

Kokal

Vanamala

Dave

2023

JCP

View full text Add to dashboard Cite

Throughout the past several decades, mobile devices have evolved in capability and popularity at growing rates while improvement in security has fallen behind. As smartphones now hold mass quantities of sensitive information from millions of people around the world, addressing this gap in security is crucial. Recently, researchers have experimented with behavioral and physiological biometrics-based authentication to improve mobile device security. Continuing the previous work in this field, this study identifies popular dynamics in behavioral and physiological smartphone authentication and aims to provide a comprehensive review of their performance with various deep learning and machine learning algorithms. We found that utilizing hybrid schemes with deep learning features and deep learning/machine learning classification can improve authentication performance. Throughout this paper, the benefits, limitations, and recommendations for future work will be discussed.

show abstract

“…Researchers of [28][29][30] chose other ML classifiers for their models. In study [28], a continuous touch-dynamics authentication method was studied.…”

Section: Literature Reviewmentioning

confidence: 99%

Section: Literature Reviewmentioning

confidence: 99%