I Think, Therefore I Am: Usability and Security of Authentication Using Brainwaves

Abstract

Abstract. With the embedding of EEG (electro-encephalography) sensors in wireless headsets and other consumer electronics, authenticating users based on their brainwave signals has become a realistic possibility. We undertake an experimental study of the usability and performance of user authentication using consumer-grade EEG sensor technology. By choosing custom tasks and custom acceptance thresholds for each subject, we can achieve 99% authentication accuracy using single-channel EEG signals, which is on par with previous research employing multichannel EEG signals using clinical-grade devices. In addition to the usability improvement offered by the single-channel dry-contact EEG sensor, we also study the usability of different classes of mental tasks. We find that subjects have little difficulty recalling chosen "pass-thoughts" (e.g., their previously selected song to sing in their mind). They also have different preferences for tasks based on the perceived difficulty and enjoyability of the tasks. These results can inform the design of authentication systems that guide users in choosing tasks that are both usable and secure.

An Online Synchronous Brain Wave Signal Pattern Classifier with Parallel Processing Optimization for Embedded System Implementation

“…For the single electrode case, relevant work has been done with supervised learning feature extraction (ANN)and linear discriminant analysis LDA for stress signal wave generation with the use of MATLAB [27] from single electrode raw EEG signal extraction. Other works make use of the similarity components of signals generated by pass-thoughts in order to classify certain conditions than can also be used for authentication purposes [28]. Other low cost targeted bio-sensing methods for electrocardiograms with small embedded systems are using Linear SVM Classification after proper signal processing [29].…”

Improving Physiological Signal Classification Using Logarithmic Quantization and a Progressive Calibration Technique

“…Traditionally, BCI applications rely on dense, high-dimensional feature vectors produced by multi-electrode scanning caps with high temporal resolution (Lotte et al, 2007), which threatens the responsiveness of BCI from a user experience standpoint and places high requirements on end-user hardware. (Crowley et al, 2010;Grierson and Kiefer, 2011;Chuang et al, 2013;Johnson et al, 2014). However, the use of consumer EEGs for the direct, real-time control of software interfaces has proven more difficult, as the number of electrodes on these headsets limit the spatial resolution required to discriminate between mental gestures (Carrino et al, 2012;Larsen and Hokl, 2011).…”

“…We obtained an anonymized dataset of EEG recordings from 15 subjects, all students at UC Berkeley, performing seven mental gestures in a sitting position over two sessions (Chuang et al, 2013). The signals were recorded using a consumer-grade EEG headset, the Neurosky MindSet, with a dry contact EEG sensor over the Fp1 position.…”

“…Each of the ten trials lasted ten seconds. The seven mental gestures were: (i) breathing with eyes closed; (ii) motor imagery of right index finger movement; (iii) motor imagery of subject's choice of repetitive sports motion; (iv) mentally sing a song or recite a passage; (v) listen for an audio tone with eyes closed; (vi) visual counting of rectangles of a chosen color on a computer screen; and (vii) any mental thought of subject's choice (Chuang et al, 2013).…”

My thoughts are not your thoughts

“…Over the last two years, a number of researchers have investigated the serious possibility of using consumer-grade single-channel brainwave signal readers to authenticate users into a computer system. The first such project [3] involved a recruited user base of 15 students, who gave samples of their brainwave signals for a set of 7 tasks. The authors developed a rubric for matching the data from those signals to their originating subjects, and designed an authentication system based on task customization with a failure rate as low as 1%.…”