Enhancing the Security of Pattern Unlock with Surface EMG-Based Biometrics

Abstract

Pattern unlock is a popular screen unlock scheme that protects the sensitive data and information stored in mobile devices from unauthorized access. However, it is also susceptible to various attacks, including guessing attacks, shoulder surfing attacks, smudge attacks, and side-channel attacks, which can achieve a high success rate in breaking the patterns. In this paper, we propose a new two-factor screen unlock scheme that incorporates surface electromyography (sEMG)-based biometrics with patterns for user authentication. sEMG signals are unique biometric traits suitable for person identification, which can greatly improve the security of pattern unlock. During a screen unlock session, sEMG signals are recorded when the user draws the pattern on the device screen. Time-domain features extracted from the recorded sEMG signals are then used as the input of a one-class classifier to identify the user is legitimate or not. We conducted an experiment involving 10 subjects to test the effectiveness of the proposed scheme. It is shown that the adopted time-domain sEMG features and one-class classifiers achieve good authentication performance in terms of the F 1 score and Half of Total Error Rate (HTER). The results demonstrate that the proposed scheme is a promising solution to enhance the security of pattern unlock.

Performance Optimization of Surface Electromyography Based Biometric Sensing System for Both Verification and Identification

“…However, it has been shown that for a short time contraction, the sEMG signals satisfy the stationary assumptions [31]. Therefore, for a short duration, isometric contractions suitable for biometric applications [10][11][12], the time domain and frequency domain features are ideal for feature extraction as their mean and variances have minimal variations [32]. These include Hudgin's time-domain (TD) feature set [24] and two frequency domain feature sets: Frequency division technique (FDT) [21,26] and Autoregressive coefficients (AR) [27,33].…”

“…It is likely that they will find applications in low-risk authentication scenarios, complementary to other well-established biometric modalities. Although multiple studies have investigated EEG and ECG as a biometric trait, there have been limited studies that use surface electromyogram (sEMG) from the forearm and hand muscles while performing hand gestures [6,[10][11][12]. Due to the characteristic property that different movements result in distinctive EMG patterns, sEMG has been predominantly used for accurate hand gesture recognition [13][14][15].…”

“…The feature extraction involved a combination of time-frequency-spatial domain features as well as HD-EMG decomposition-based features. A recent study utilized only one electrode placed on the flexor digitorum superficialis muscle while the participants performed a phone unlock pattern with contractions of their fingers [12]. The time-domain feature extraction method was employed on the sEMG signals.…”

Development of Miniaturized Wearable Wristband Type Surface EMG Measurement System for Biometric Authentication

“…In contrast, the EMG-based authentication systems are more suitable because they are not influenced by the surrounding noise or the health of the user. Therefore, authentication studies using EMG signals have been actively conducted in the recent years [11][12][13][14].…”

“…In a previous study, the EMG signal was used to unlock the pattern lock by drawing a pattern after attaching a wet electrode to the forearm, and data were classified using a oneclass classification algorithm [13]. These previously proposed methods are inconvenient owing to the following reasons: The size of the motion must be large, and the sample signal must be set for each person.…”