S3: An AI-Enabled User Continuous Authentication for Smartphones Based on Sensors, Statistics and Speaker Information

Abstract

Continuous authentication systems have been proposed as a promising solution to authenticate users in smartphones in a non-intrusive way. However, current systems have important weaknesses related to the amount of data or time needed to build precise user profiles, together with high rates of false alerts. Voice is a powerful dimension for identifying subjects but its suitability and importance have not been deeply analyzed regarding its inclusion in continuous authentication systems. This work presents the S3 platform, an artificial intelligence-enabled continuous authentication system that combines data from sensors, applications statistics and voice to authenticate users in smartphones. Experiments have tested the relevance of each kind of data, explored different strategies to combine them, and determined how many days of training are needed to obtain good enough profiles. Results showed that voice is much more relevant than sensors and applications statistics when building a precise authenticating system, and the combination of individual models was the best strategy. Finally, the S3 platform reached a good performance with only five days of use available for training the users’ profiles. As an additional contribution, a dataset with 21 volunteers interacting freely with their smartphones for more than sixty days has been created and made available to the community.

A Supervised ML Biometric Continuous Authentication System for Industry 4.0

“…The most common combination is the use of sensors together with another type of source. For example, sensors and statistics [12], [13], sensors and touch screen data [14], [15], or sensors, statistics, and voice in [6]. The work at [16] stands out for a design where seven different kinds of data are used.…”

“…Sensors existing S3 Platform. Since this work not only extends but also compares the utility and performance of [6], for the sake of self-containment, a short description of the S3 platform is provided.…”

“…A noteworthy difference of this work with the one proposed in [6] is that, because it is an industrial environment, and the safety and efficiency of the worker are prioritized, the operators, when they operate with the device, usually do it in a single mode way. For example, if the operator uses voice commands, it is usual that (s)he uses it with voice only, since this allows him/her to have hands free in order to perform particularly hand use intensive tasks.…”

“…For each user, once there is enough data collected by the application to generate the behavioral profiles, these are extracted by the framework using outlier detection algorithms, using only the user's data. More details of the S3 platform can be found in [6]. A new extension of the S3 for this work is proposed to include several devices, not only smartphones and to support supervised algorithms.…”

“…Research on biometric authentication systems in Industry 4.0 is very limited, and it is focused on the use of simple biometrics, such as iris, fingerprints, among all. In a recent paper [6], a platform (S3 Platform) for the combined use of sensors, statistics and voice data for CA was proposed. In that work, only an unsupervised Machine Learning approach was considered, as its creators were concerned with possible legal restrictions.…”