Touch-dynamics based Behavioural Biometrics on Mobile Devices – A Review from a Usability and Performance Perspective

Abstract

Over the past few years, there has been an exponential increase in the percentage of people owning and using a smart phone. These devices have sensor-rich touchscreens that can capture sensitive biometric features such as keystroke typing and finger-swiping patterns. Touch-dynamics based behavioural biometrics is a time-based assessment of how a user performs a particular touch task on a mobile device. Several performance-focused surveys already exist. In this article, building upon the existing reviews, we have examined studies on touch-dynamics based behavioural biometrics based on usability and its impact on authentication performance. We also emphasize the need for shifting the focus on usability during performance evaluations by presenting a consolidated list of usability and ergonomic-based factors that influence user interaction and cause performance variations. In this article, we report and review the usability evaluations: user acceptance studies and performance-based studies influencing the user interaction process on three specific touch-dynamics based modalities—signature, keystroke, and swipe. With regards to performance, we present a comparative analysis of error rates and accuracy of various research works undertaken. Additionally, we present a consolidated list of public datasets and discuss evolving vulnerabilities of touch-dynamics based behavioural biometrics, their adopted attack models, and their feasibility. Finally, we present our assessment of this domain's existing unresolved problems that could pave the way for future research.

Defending Touch-based Continuous Authentication Systems from Active Adversaries Using Generative Adversarial Networks

“…Machine learning-based matchers, on the other hand, achieve much lower error rates, therefore, heavily studied for implementing TCAS [6,12,19] than the distance-based matchers. Therefore, we chose to experiment with machine learning-based implementations of TCAS.…”

“…One of the primary reasons behind this is that touch gestures meet most of the criteria (universality, distinctiveness, permanence, collectability, *Authors contributed equally. 2021 IEEE International Joint Conference on Biometrics (IJCB) 978-1-6654-3780-6/21/$31.00 ©2021 IEEE performance, acceptability, and circumvention) that are defined to be viable biometric [12,13].…”

Online Handwriting, Signature and Touch Dynamics: Tasks and Potential Applications in the Field of Security and Health

“…Keystroke dynamics have been extensively used for identification aims on physical keyboards [69,5,97] and recently on virtual keyboards when considering smartphones and tablets [98]. In this last situation a wider range of interactions can be considered including finger-swiping patterns drawing, touch-dynamics and, of course, signatures [47,23]. It is evident that aspects involved in handwriting/signing described in the previous sections are not far from those involved in more general hand-based interaction tasks because they involve the same hand motor area within the brain [32].…”

A Survey of Privacy Vulnerabilities of Mobile Device Sensors

“…Mobile devices such as smartphones, tablets, and wearables are provided with several sensors that are able to acquire a vast amount of personal information in different forms and for different purposes. This aspect, in combination with the significant advancements of the computational and communication capabilities of mobile devices over the last years, has shown the high potential of mobile devices in many application fields [101,56,157]. The large availability of personal data generated on mobile devices, in combination with their ubiquity (with 3.9 billion smartphones globally in 2016, estimated to rise to 6.8 billion by 2022 [70]) and their always-on nature has turned this technology into a potential source of major invasion of persona privacy.…”