Ensuring the privacy of the personal data stored in our technological devices is a fundamental aspect for protecting our personal and professional information. Authentication procedures are among the main methods used to achieve this protection and, typically, are implemented only when accessing to the device. Nevertheless, in many occasions it is necessary to carry out this authentication in a continuous manner to guarantee an allowed use of the device while protecting the authentication data. In this work, we first review the state of the art of Continuous Authentication (CA) and related privacy–preserving methods and, secondly, propose a CA scheme using sensor–based data and machine learning algorithms, that ensures the protection of the information via Format–Preserving Encryption with a unique and secret key per user. Our experimental results on a real–world dataset show the suitability of the proposed scheme, featuring 76.85% of accuracy while respecting users privacy.
ACKNOWLEDGEMENTS. The author would like to thank to J.M. de Fuentes, L. Gonz´alez Manzano, L. Hern´andez Encinas for their valuable help, and to CSIC Project 202050E304 (CASDiM).