Mobile Match-on-Card Authentication Using Offline-Simplified Models with Gait and Face Biometrics

Abstract

Biometrics have become important for mobile authentication, e.g. to unlock devices before using them. One way to protect biometric information stored on mobile devices from disclosure is using embedded smart cards (SCs) with biometric match-on-card (MOC) approaches. However, computational restrictions of SCs also limit biometric matching procedures. We present a mobile MOC approach that uses offline training to obtain authentication models with a simplistic internal representation in the final trained state, wherefore we adapt features and model representation to enable their usage on SCs. The pre-trained model can be shipped with SCs on mobile devices without requiring retraining to enroll users. We apply our approach to acceleration based mobile gait authentication as well as face authentication and compare authentication accuracy and computation time of 16 and 32 bit Java Card SCs. Using 16 instead of 32 bit SCs has little impact on authentication performance and is faster due to less data transfer and computations on the SC. Results indicate 11.4% and 2.4-5.4% EER for gait respectively face authentication, with transmission and computation durations on SCs in the range of 2 s respectively 1 s. To the best of our knowledge this work represents the first practical approach towards acceleration based gait MOC authentication.

Multifactor Authentication Protocol in a Mobile Environment

“…Another mechanism for confirming the user's identity involves using a Smart Card [19]. Since SC computing capabilities are limited, the developers of the solution proposed a simplified protocol for comparing biometric features that can be implemented using of devices of this class.…”

“…The use of fixed IMEI and IMSI values allows one to confirm that the authentication request comes from a device associated with the user during the registration process; however, these are values that can be read by any application installed on the mobile device. For other schemes, such as those presented in [16]- [19], according to section 2.3.1 of Regulation [1] relating to the authentication mechanism, a high level of trust is required from the scheme used to implement dynamic authentication. Within such a process, the factor that serves as evidence of the identity of the user must be changed whenever authentication is attempted.…”

Review on Reliable Pattern Recognition with Machine Learning Techniques

“…Findling and Mayrhofer [35] proposed a pan shot face unlock method: a mobile device unlock mechanism using all information available from a 180-degree pan shot of the device around the user's head. For face recognition, they evaluated different support vector machines and neural networks, and the results demonstrated the feasibility of their approach.…”

Recent Advances in Biometric Technology for Mobile Devices

“…One interesting recent trend of research relates to the fusion of physiological and behavioral traits, which brings to the fore high recognition accuracies (due to the physiological trait), as well as continuous authentication (due to the behavioral trait). Satisfactory results of EER = 2.4% have been achieved in this area for example employing face and voice [30]. This is only a recent trend and it will be important to explore different traits, in order to find reasonable combinations of physiological and behavioral traits to attend a robust and reliable mobile solution.…”