Visible to the public Spectral Keyboard Streams: Towards Effective and Continuous Authentication

TitleSpectral Keyboard Streams: Towards Effective and Continuous Authentication
Publication TypeConference Paper
Year of Publication2017
AuthorsAlshehri, A., Coenen, F., Bollegala, D.
Conference Name2017 IEEE International Conference on Data Mining Workshops (ICDMW)
ISBN Number978-1-5386-1480-8
Keywordsauthentication, behavioral biometric, benchmark feature vector representation, Continuous Authentication, discrete Fourier transform, Discrete Fourier transforms, discrete wavelet transform, discrete wavelet transforms, Human Behavior, human factors, keyboard dynamics, keyboard user monitoring, Keyboards, keystroke analysis, keystroke dynamics, Keystroke Streams, keystroke time series, learning (artificial intelligence), Metrics, on-line assessment, online learning platforms, pubcrawl, robust authentication mechanisms, spectral keyboard streams, time series, Time series analysis, Timing, Vectors
Abstract

In this paper, an innovative approach to keyboard user monitoring (authentication), using keyboard dynamics and founded on the concept of time series analysis, is presented. The work is motivated by the need for robust authentication mechanisms in the context of on-line assessment such as those featured in many online learning platforms. Four analysis mechanisms are considered: analysis of keystroke time series in their raw form (without any translation), analysis consequent to translating the time series into a more compact form using either the Discrete Fourier Transform or the Discrete Wavelet Transform, and a "benchmark" feature vector representation of the form typically used in previous related work. All four mechanisms are fully described and evaluated. A best authentication accuracy of 99% was obtained using the wavelet transform.

URLhttp://ieeexplore.ieee.org/document/8215670/
DOI10.1109/ICDMW.2017.38
Citation Keyalshehri_spectral_2017