Continuous user authentication via unlabeled phone movement patterns

Abstract

In this paper, we propose a novel continuous authentication system for smartphone users. The proposed system entirely relies on unlabeled phone movement patterns collected through smartphone accelerometer. The data was collected in a completely unconstrained environment over five to twelve days. The contexts of phone usage were identified using k-means clustering. Multiple profiles, one for each context, were created for every user. Five machine learning algorithms were employed for classification of genuine and impostors. The performance of the system was evaluated over a diverse population of 57 users. The mean equal error rates achieved by Logistic Regression, Neural Network, kNN, SVM, and Random Forest were 13.7%, 13.5%, 12.1%, 10.7%, and 5.6% respectively. A series of statistical tests were conducted to compare the performance of the classifiers. The suitability of the proposed system for different types of users was also investigated using the failure to enroll policy. 1

Human Activity Recognition using Smartwatch and Smartphone: A Review on Methods, Applications, and Challenges

“…Several footprints behavior have been investigated for continuously authenticating persons [51]. Recently, the movement pattern of phone was worked on by Balagani et al [52], which concentrated basically on phone movement patterns during walking and sitting for continuous authentication of smartphone's user by employed a Hand Movement, Orientation, and Grasp (HMOG) as a set of behavioral features , whereas, Kumar et al [53] proposed an authentication system that depends on phone movement patterns during typing or swiping collected from a diverse population in an unrestricted environments. The results stated that may not be adequate for a certain types user and would presented high error rate, and the movement pattern of the phone based authentication systems may not be suitable for every smartphone user.…”

Identification of internal faults in indirect symmetrical phase shift transformers using ensemble learning

“…The approach was further extended to multivariate time series by Wirth et al [17]. Kumar et al [18,19] classified genuine and illegitimate users by computing a variety of features from time, frequency, and power domains. The specific features included band power, spectral entropy, median frequency, histogram (16 bins), range, peak magnitude to root mean square ratio, std, inter-quartile range, correlation, mutual information and DTW distances between a pair of two signals that were extracted from time series signals captured by accelerometer and gyroscope sensors.…”

“…The approach was further extended to multivariate time series by Wirth et al [17]. Kumar et al [18,19] Morchen [20] transformed the time series to wavelet and frequency domains to classify among 17 time-series datasets. Timmer et al [21] computed features from both time and frequency domains to categorize hand tremor time series.…”

On the Inference of Soft Biometrics from Typing Patterns Collected in a Multi-device Environment

“…body movements [Kumar et al 2017], and fusion are some of the widely studied behavioral patterns in the context of desktop, mobile, and wearable devices. Typing is commonly characterized as key press and release timings, keystroke sounds, and video sequence [Banerjee and Woodard 2012;Roth et al 2014Roth et al , 2015Teh et al 2013].…”