Search for: All records

While developing continuous authentication systems (CAS), we generally assume that samples from both genuine and impostor classes are readily available. However, the assumption may not be true in certain circumstances. Therefore, we explore the possibility of implementing CAS using only genuine samples. Specifically, we investigate the usefulness of four one-class classifiers OCC (elliptic envelope, isolation forest, local outliers factor, and one-class support vector machines) and their fusion. The performance of these classifiers was evaluated on four distinct behavioral biometric datasets, and compared with eight multi-class classifiers (MCC). The results demonstrate that if we have sufficient training data from the genuine user the OCC, and their fusion can closely match the performance of the majority of MCC. Our findings encourage the research community to use OCC in order to build CAS as it does not require knowledge of impostor class during the enrollment process. 

Wearable computing devices have become increasingly popular and while these devices promise to improve our lives, they come with new challenges. One such device is the Google Glass from which data can be stolen easily as the touch gestures can be intercepted from a head-mounted device. This paper focuses on analyzing and combining two behavioral metrics, namely, head movement (captured through glass) and torso movement (captured through smartphone) to build a continuous authentication system that can be used on Google Glass alone or by pairing it with a smartphone. We performed a correlation analysis among the features on these two metrics and found that very little correlation exists between the features extracted from head and torso movements in most scenarios (set of activities). This led us to combine the two metrics to perform authentication. We built an authentication system using these metrics and compared the performance among different scenarios. We got EER less than 6% when authenticating a user using only the head movements in one scenario whereas the EER is less than 5% when authenticating a user using both head and torso movements in general. 

Free-text keystroke is a form of behavioral biometrics which has great potential for addressing the security limitations of conventional one-time authentication by continuously monitoring the user's typing behaviors. This paper presents a new, enhanced continuous authentication approach by incorporating the dynamics of both keystrokes and wrist motions. Based upon two sets of features (free-text keystroke latency features and statistical wrist motion patterns extracted from the wrist-worn smartwatches), two one-vs-all Random Forest Ensemble Classifiers (RFECs) are constructed and trained respectively. A Dynamic Trust Model (DTM) is then developed to fuse the two classifiers' decisions and realize non-time-blocked real-time authentication. In the free-text typing experiments involving 25 human subjects, an imposter/intruder can be detected within no more than one sentence (average 56 keystrokes) with an FRR of 1.82% and an FAR of 1.94%. Compared with the scheme relying on only keystroke latency which has an FRR of 4.66%, an FAR of 17.92% and the required number of keystroke of 162, the proposed authentication system shows significant improvements in terms of accuracy, efficiency, and usability. 

Abstract: In the past few years, smart mobile devices have become ubiquitous. Most of these devices have embedded sensors such as GPS, accelerometer, gyroscope, etc. There is a growing trend to use these sensors for user identification and activity recognition. Most prior work, however, contains results on a small number of classifiers, data, or activities. We present a comprehensive evaluation often representative classifiers used in identification on two publicly available data sets (thus our work is reproducible). Our results include data obtained from dynamic activities, such as walking and running; static postures such as sitting and standing; and an aggregate of activities that combine dynamic, static, and postural transitions, such as sit-to-stand or stand-to-sit. Our identification results on aggregate data include both labeled and unlabeled activities. Our results show that the k-Nearest Neighbors algorithm consistently outperforms other classifiers. We also show that by extracting appropriate features and using appropriate classifiers, static and aggregate activities can be used for user identification. We posit that this work will serve as a resource and a benchmark for the selection and evaluation of classification algorithms for activity based identification on smartphones.