Keystroke dynamics for user authentication

Abstract

In this paper we investigate the problem of user authentication using keystroke biometrics. A new distance metric that is effective in dealing with the challenges intrinsic to keystroke dynamics data, i.e., scale variations, feature interactions and redundancies, and outliers is proposed. Our keystroke biometrics algorithms based on this new distance metric are evaluated on the CMU keystroke dynamics benchmark dataset and are shown to be superior to algorithms using traditional distance metrics. IntroductionWith the ever increasing demand for more secure access control in many of today's security applications, traditional methods such as PINs, tokens, or passwords fail to keep up with the challenges presented because they can be lost or stolen, which compromises the system security. [26] provides a natural choice for secure "password-free" computer access. Keystroke dynamics refers to the habitual patterns or rhythms an individual exhibits while typing on a keyboard input device. These rhythms and patterns of tapping are idiosyncratic [5], in the same way as handwritings or signatures, due to their similar governing neurophysiological mechanisms. As early as in the 19 th century, telegraph operators could recognize each other based on one's specific tapping style [18]. This suggests that keystroke dynamics contain sufficient information to serve as a potential biometric identifier to ascertain a specific keyboard user.Compared to other biometrics, keystroke biometrics has additional desirable properties due to its user-friendliness and non-intrusiveness. Keystroke dynamics data can be collected without a user's cooperation or even awareness.Continuous authentication is possible using keystroke dynamics just as a mere consequence of people's use of computers. Unlike many other biometrics, the temporal information of keystrokes can be collected to ascertain a user using only software and no additional hardware. In summary, keystroke dynamics biometrics enables a cost effective, user friendly, and continuous user authentication with potential for high accuracy.Although keystroke dynamics is governed by a person's neurophysiological pathway to be highly individualistic, it can also be influenced by his or her psychological state. As a "behavioral" biometrics [35], keystroke dynamics exhibits instabilities due to transient factors such as emotions, stress, and drowsiness etc [6]. It also depends on external factors, such as the input keyboard device used, possibly due to different layout of the keys. The keying times can be noisy with outliers. As keystroke biometrics exploits the habitual rhythm in typing, it has been observed that keystrokes of frequently typed words or strings show more consistency and are better discerners [22][38].Keystroke biometrics can use "static text", where keystroke dynamics of a specific pre-enrolled text, such as a password, is analyzed at a certain time, e.g., during the log on process. For more secure applications, "free text" should be used to continuously authenticate a user...

Towards Predicting Good Users for Biometric Recognition Based on Keystroke Dynamics

“…The related works are focused mostly on outliers removal [18] [19] and features improvement [20] [21]. The outliers can be defined as samples with an unusual pattern in comparison with the available data from a specific user.…”

“…The experimental protocol is the same as employed in popular benchmarks [18] [19]. The 200 samples from the first 4 sessions are used as gallery/enrollment set.…”

“…In this paper we evaluate two popular recognition algorithms for keystroke dynamics [18] [19]. Both approaches have achieved the most competitive performances reported for the CMU benchmark dataset among more than 14 different systems.…”

“…-System A -Modified Manhattan distance with Nearest Neighbor classifier [18]: this system is based on a combination of the Manhattan and the Mahalanobis distances. The method can be summarized as (see [18] for details): i) the feature vectors are normalized according principles inspired by the Mahalanobis distance (using the covariance matrix) and; ii) the normalized feature vectors are matched with the enrollment data using the Manhattan distance and a Nearest Neighbor classifier.…”

Score normalization for keystroke dynamics biometrics

“…• Combined Manhattan-Mahalannobis distance: this distance metric was proposed in [16]. The test samples and the enrollment set are first normalized as ⁄ T and ⁄ T , where is the covariance matrix of the enrollment set.…”