Secure and Usable User-in-a-Context Continuous Authentication in Smartphones Leveraging Non-Assisted Sensors

Abstract

Smartphones are equipped with a set of sensors that describe the environment (e.g., GPS, noise, etc.) and their current status and usage (e.g., battery consumption, accelerometer readings, etc.). Several works have already addressed how to leverage such data for user-in-a-context continuous authentication, i.e., determining if the porting user is the authorized one and resides in his regular physical environment. This can be useful for an early reaction against robbery or impersonation. However, most previous works depend on assisted sensors, i.e., they rely upon immutable elements (e.g., cell towers, satellites, magnetism), thus being ineffective in their absence. Moreover, they focus on accuracy aspects, neglecting usability ones. For this purpose, in this paper, we explore the use of four non-assisted sensors, namely battery, transmitted data, ambient light and noise. Our approach leverages data stream mining techniques and offers a tunable security-usability trade-off. We assess the accuracy, immediacy, usability and readiness of the proposal. Results on 50 users over 24 months show that battery readings alone achieve 97.05% of accuracy and 81.35% for audio, light and battery all together. Moreover, when usability is at stake, robbery is detected in 100 s for the case of battery and in 250 s when audio, light and battery are applied. Remarkably, these figures are obtained with moderate training and storage needs, thus making the approach suitable for current devices.

Improving the Security and QoE in Mobile Devices through an Intelligent and Adaptive Continuous Authentication System

“…In addition, the energy consumption of their system is higher than the consumption of ours. On the other hand, the work proposed by de Fuentes et al [ 21 ] performs a user classification based on non-assisted sensors achieving 97% of accuracy using only battery reading information. When the system tries to identify both user and environment by combining data from different sensors, like battery readings, ambient light and ambient noise sensors, it obtains 81.35% of accuracy.…”

“…The ML method selected was One-Class SVM [ 19 ] after comparing it to others like Kernel Ridge Regression (KRR) [ 20 ] and k-Nearest Neighbours (kNN). Another interesting solution is the proposed by de Fuentes et al [ 21 ]. The authors of this work used non-assisted sensors, such as battery, transmitted data, ambient light and noise to authenticate the user.…”

Privacy-Preserving Sensor-Based Continuous Authentication and User Profiling: A Review

“…The work presented in [ 11 ] studied the utility of information representing battery consumption, transmitted data, and background noise and light (and combinations of them) for CA. The information, collected from the SherLock database, permits the device to work autonomously on the CA process, as it is non-assisted sensorial data.…”

Dense Deep Neural Network Architecture for Keystroke Dynamics Authentication in Mobile Phone

“…The heartbeat signal can be used as a unique feature to authenticate smartphone users. In [25], the author explored four mobile phone non assisted sensors; transmitted data, noise, battery and ambient light to develop a continuous user authentication based on KNN. The KNN classifier achieved a reasonable accuracy.…”