How Artificial Intelligence can be used for Behavioral Identification?

Nowadays, users interact with computer systems. Behavioral biometrics consists of analyzing user's interactions for identification and verification applications. This approach could be very useful for enhancing security and improving user experience and many privacy concerns are also related. In this paper, we address the problem of user identification considering their behaviors. How efficient are classical machine learning methods on such data? What about deep learning approaches? We illustrate this work on two behavioral modalities namely human activity using smartphones and keystroke dynamics on a laptop. Since the accuracy rates of most behavioral biometrics modalities are lower than morphological ones, we consider two approaches for these modalities that can be represented as time series: classical machine learning and deep learning techniques. We intend to show that many algorithms can obtain very good performance for different modalities without any specific tuning to the considered modality. This comparative analysis allows us to show that behavioral biometrics can be used for security applications (i.e. who is accessing the company information system) but could be a privacy concern as a user could be identified while navigating on the Internet.