Two novel biometric features in keystroke dynamics authentication systems for touch screen devices

Abstract

After verifying the correctness of the password, the keystroke dynamics‐based authentication (KDA) system will verify the corresponding keystroke features. It provides additional security verification for alphanumeric‐based and personal identification number‐based authentication schemes that suffer from guessing and shoulder surfing attacks. Except for the original time features in the KDA schemes, two novel keystroke features are found in touch screen handheld mobile devices, which are called “pressure” features and “size” features. A computation efficient statistical classifier is built for low‐power mobile devices to authenticate the user's identity. This paper analyzes the following combinations of features: (1) time features; (2) time features and pressure features; (3) time features and size features; and (4) all features combined. The result shows that the size features or the pressure features can effectively promote the utility of the KDA system in personal identification number‐based authentication schemes for touch screen handled mobile devices. The combination of time features and pressure features is the best one for authenticating users. Copyright © 2013 John Wiley & Sons, Ltd.

I Sensed It Was You: Authenticating Mobile Users with Sensor-Enhanced Keystroke Dynamics

“…They reported a 1% EER using a kNN algorithm and later obtained similar results using neural networks [48]. More recent studies on real mobile devices seem to suggest that pressure has a much smaller accuracy impact in practice, ultimately resulting in a 8.4% EER when combined with keystroke timings [55]. Huang et al [23] first explored traditional keystroke dynamics techniques on software keyboards for mobile devices and reported a 7.5% EER, but only when raising an alarm after 2 consecutive failed authentication attempts.…”

“…Unfortunately, we cannot directly compare our sensor-related accuracy results with prior work, given that we are the first to explore sensor-enhanced keystroke dynamics on mobile devices. Recent work by Tasi et al [55] comes conceptually close, investigating how to improve the accuracy of keystroke dynamics techniques using pressure information. Their reported EER values, however, are as high as 8.4%, with pressure information only introducing relatively small accuracy improvements with respect to their keystroke timing-only configuration (11.4% EER).…”

“…Authentication can be performed via fixed-text analysis (i.e., with the user typing some predetermined text) [7,13,20,25,28,31,32,36,42,46] or via free-text analysis (i.e., with the user typing freely on the keyboard) [14,41]. Keystroke dynamics techniques have been explored for a broad range of devices, equipped with either hardware [26,29] or software (also called "soft") keyboards [56]-with recent work on mobile devices largely falling into the latter category [23,55,56]. While different classes of keyboards (i.e., hardware vs. software, numeric vs. alphabetic, etc.)…”

“…[56] 5.26% F RR, 8.31% F AR [55] 8.40% EER Table 2. Accuracy comparison with prior keystroke dynamics techniques.…”

Biometric Swiping on Touchscreens

“…Tasia et. al [22] also proposed a twelve key virtual keypad as an interface for users to enter their biometric pins. The result is encouraging that they achieved a constant 8.4% EER.…”