Statistical Keystroke Dynamics System on Mobile Devices for Experimental Data Collection and User Authentication (original) (raw)
Related papers
Keystroke dynamics identity verification—its problems and practical solutions
Computers & Security, 2004
Password is the most widely used identity verification method in computer security domain. However, because of its simplicity, it is vulnerable to imposter attacks. Use of keystroke dynamics can result in a more secure verification system. Recently, Cho et al. (J Organ Comput Electron Commerce 10 proposed autoassociative neural network approach, which used only the user's typing patterns, yet reporting a low error rate: 1.0% false rejection rate (FRR) and 0% false acceptance rate (FAR). However, the previous research had some limitations: (1) it took too long to train the model; (2) data were preprocessed subjectively by a human; and (3) a large data set was required. In this article, we propose the corresponding solutions for these limitations with an SVM novelty detector, GAeSVM wrapper feature subset selection, and an ensemble creation based on feature selection, respectively. Experimental results show that the proposed methods are promising, and that the keystroke dynamics is a viable and practical way to add more security to identity verification. ª
Feature Selection in Keystroke Dynamics Authentication Systems
International Conference on Computer, Information Technology and Digital Media (CITaDIM2013), 2013
Keystroke dynamics is a way for detecting impostors which use the analysis of typing rhythms to discriminate among users. It shows people’s behavioral features which are similar to hand signatures. Many features are used in keystroke dynamics such as key-press time, inter-key time, finger placement and applied pressure. We aim to find more important or discriminative features in this domain, so we implement four feature selection methods include one pure filter and three wrappers on a benchmark keystroke dynamics data set. Experimental results showed that the key holding time is one of the major features in the keystroke dynamics authentication systems.
KSII Transactions on Internet and Information Systems
Nowadays, most users access internet through mobile applications. The common way to authenticate users through websites forms is using passwords; while they are efficient procedures, they are subject to guessed or forgotten and many other problems. Additional multi modal authentication procedures are needed to improve the security. Behavioral authentication is a way to authenticate people based on their typing behavior. It is used as a second factor authentication technique beside the passwords that will strength the authentication effectively. Keystroke dynamic rhythm is one of these behavioral authentication methods. Keystroke dynamics relies on a combination of features that are extracted and processed from typing behavior of users on the touched screen and smart mobile users. This Research presents a novel analysis in the keystroke dynamic authentication field using two features categories: timing and no timing combined features. The proposed model achieved lower error rate of false acceptance rate with 0.1%, false rejection rate with 0.8%, and equal error rate with 0.45%. A comparison in the performance measures is also given for multiple datasets collected in purpose to this research.
User Authentication Using Keystroke Dynamics based of Selected Features
Keystroke dynamics is the time analysis of a users typing habit. Keystroke dynamics is a biometric method of user authentication. However an authentication technique must strive to balance two properties: speed; accuracy. In order to balance these conflicting properties, a small set of accurate features and a simplistic measurement technique. These are the measures of flight time, dwell time, and latency time, and the technique of confidence interval based statistical analysis.
Keystroke Biometric System Test Taker Setup and Data Collection
2010
Pace University has been conducting keystroke biometric research for seven years. The system under development has the capability of identifying or authenticating users from typing characteristics and patterns. It consists of three primary components: a keystroke entry system that collects data over the Internet, a feature extractor, and a pattern classifier. This paper is focused on the keystroke entry system component and enhancements made to it to support the biometric authentication of students taking tests over the Internet. The keystroke entry system is enhanced to operate in stealth or background mode so that a user’s typing characteristics and patterns can be captured anonymously while the user participates in an online test. The system compares test and enrollment samples to authenticate test takers.
User authentication through typing biometrics features
IEEE Transactions on Signal Processing, 2005
This paper uses a static keystroke dynamics in user authentication. The inputs are the key down and up times and the key ASCII codes captured while the user is typing a string. Four features (key code, two keystroke latencies, and key duration) were analyzed and seven experiments were performed combining these features. The results of the experiments were evaluated with three types of user: the legitimate, the impostor and the observer impostor users. The best results were achieved utilizing all features, obtaining a false rejection rate of 1.45% and a false acceptance rate of 1.89%. This approach can be used to improve the usual login-password authentication when the password is no more a secret. This paper innovates using four features to authenticate users.
A Study And Analysis of Keystroke Dynamics And Its Enhancement For Proficient User Authentication
in this paper we proposed one new measure of keystroke patterns over and above of the existing features for making user authentication through keystroke more efficient. With comparison to other access control systems based on biometric features, keystroke analysis has not yet meets acceptable level of accuracy. The reason is probably the intrinsic variability of typing dynamics, versus other very stable biometric characteristics, such as face or fingerprint. Our experiment and statistical analysis described in the current literature and show through experimental data that, the proposed unique measure of keystrokes can be combined with existing authentication mechanism to improve the authentication and security of delicate applications to a very high extent. It can be useful to ascertain the intruders and reject them from the system, provided that we are able to deal with the typing rhythm of the intruders. Our methodology can rely on what is typed by people because of their normal j...
An Anomaly Detector for Keystroke Dynamics Based on Medians Vector Proximity
This paper presents an anomaly detector for keystroke dynamics authentication, based on a statistical measure of proximity, evaluated through the empirical study of an independent benchmark of keystroke data. A password typing-rhythm classifier is presented, to be used as an anomaly detector in the authentication process of genuine users and impostors. The proposed user authentication method involves two phases. First a training phase in which a user typing profile is created through repeated entry of password. In the testing phase, the password typing rhythm of the user is compared with the stored typing profile, to determine whether it is a genuine user or an impostor. The typing rhythm is obtained through keystroke timings of key-down / key-up of individual keys and the latency between keys. The training data is stored as a typing profile, consisting of a vector of median values of elements of the feature set, and as a vector of standard deviations for the same elements. The proposed classifier algorithm computes a score for the typing of a password to determine authenticity. A measure of proximity is used in the comparison between feature set medians vector and feature set testing vector. Each feature in the testing vector is given a binary score of 1 if it is within a proximity distance threshold from the stored median of that feature, otherwise the score is 0. The proximity distance threshold for a feature is chosen to be the standard deviation of that feature in the training data. The typing of a password is classified as genuine if the accumulated score for all features meet a minimum acceptance threshold. Analysis of the benchmark dataset using the proposed classifier has given an improved anomaly detection performance in comparison with results of 14 algorithms that were previously tested using the same benchmark.
User authentication through keystroke dynamics
ACM Transactions on Information …, 2002
Unlike other access control systems based on biometric features, keystroke analysis has not led to techniques providing an acceptable level of accuracy. The reason is probably the intrinsic variability of typing dynamics, versus other-very stable-biometric characteristics, such as face or fingerprint patterns. In this paper we present an original measure for keystroke dynamics that limits the instability of this biometric feature. We have tested our approach on 154 individuals, achieving a False Alarm Rate of about 4% and an Impostor Pass Rate of less than 0.01%. This performance is reached using the same sampling text for all the individuals, allowing typing errors, without any specific tailoring of the authentication system with respect to the available set of typing samples and users, and collecting the samples over a 28.8-Kbaud remote modem connection.
On Continuous User Authentication via Typing Behavior
IEEE Transactions on Image Processing, 2014
We hypothesize that an individual computer user has a unique and consistent habitual pattern of hand movements, independent of the text, while typing on a keyboard. As a result, this paper proposes a novel biometric modality named "Typing Behavior (TB)" for continuous user authentication. Given a webcam pointing toward a keyboard, we develop real-time computer vision algorithms to automatically extract hand movement patterns from the video stream. Unlike the typical continuous biometrics such as keystroke dynamics (KD), TB provides reliable authentication with a short delay, while avoiding explicit key-logging. We collect a video database where 63 unique subjects type static text and free text for multiple sessions. For one typing video, the hands are segmented in each frame and a unique descriptor is extracted based on the shape and position of hands, as well as their temporal dynamics in the video sequence. We propose a novel approach, named bag of multi-dimensional phrases, to match the cross-feature and cross-temporal pattern between a gallery sequence and a probe sequence. The experimental results demonstrate superior performance of TB when compared to KD, which, together with our ultra-real-time demo system, warrant further investigation of this novel vision application and biometric modality. Index Terms-Continuous authentication, user authentication, biometrics, typing behavior, hand movements, bag of phrases, bag of multi-dimensional phrases, keystroke dynamics, keyboard. I. INTRODUCTION I T is common to validate the identity of a user for any computer system. The standard password-based, one-shot user authentication may create an information system that is vulnerable immediately after login, since no mechanism exists to continuously verify the identity of the active user. This can be an especially severe problem for security-sensitive facilities, where compromised passwords or insufficient vigilance after initial login can leak confidential information or give unwanted privileges to the user. Hence, a method enabling continuous authentication for the active user is highly desired. One popular alternative to password-based user authentication is to employ biometrics. Biometrics refers to the identification of humans by their physical characteristics (e.g., face, fingerprint, iris) or behavioral traits (e.g., gait, keystroke dynamics, mouse dynamics) [15]. Among these biometric modalities, face, fingerprint, keystroke dynamics (KD), and