A machine learning approach to keystroke dynamics based user authentication

The majority of computer systems employ a login ID and password as the principal method for access security. In stand-alone situations, this level of security may be adequate, but when computers are connected to the internet, the vulnerability to a security breach is increased. In order to reduce vulnerability to attack, biometric solutions have been employed. In this paper, we investigate the use of a behavioural biometric based on keystroke dynamics. Although there are several implementations of keystroke dynamics available, their effectiveness is variable and dependent on the data sample and its acquisition methodology. The results from this study indicate that the Equal Error Rate (EER) is significantly influenced by the attribute selection process and to a lesser extent on the authentication algorithm employed. Our results also provide evidence that a Probabilistic Neural Network (PNN) can be superior in terms of reduced training time and classification accuracy when compared with a typical MLFN back-propagation trained neural network.

[1]  Mohammad S. Obaidat,et al.  Performance of the perceptron algorithm for the classification of computer users , 1992, SAC '92.

[2]  Bassam Hussien,et al.  An application of fuzzy algorithms in a computer access security system , 1989, Pattern Recognit. Lett..

[3]  Paulo Sérgio Tenreiro Magalhães,et al.  An improved statistical keystroke dynamics algorithm , 2005 .

[4]  Xian Ke,et al.  Typing patterns: a key to user identification , 2004, IEEE Security & Privacy Magazine.

[5]  J. A. Sigüenza,et al.  FUZZY KEYSTROKE BIOMETRICS ON WEB SECURITY , 2007 .

[6]  John J. Leggett,et al.  Dynamic Identity Verification via Keystroke Characteristics , 1991, Int. J. Man Mach. Stud..

[7]  Donald F. Specht,et al.  Probabilistic neural networks , 1990, Neural Networks.

[8]  Florin Gorunescu,et al.  An evolutionary computational approach to probabilistic neural network with application to hepatic cancer diagnosis , 2005, 18th IEEE Symposium on Computer-Based Medical Systems (CBMS'05).

[9]  Claudia Picardi,et al.  User authentication through keystroke dynamics , 2002, TSEC.

[10]  Norman Shapiro,et al.  Authentication by Keystroke Timing: Some Preliminary Results , 1980 .

[11]  Mohammad S. Obaidat,et al.  A Simulation Evaluation Study of Neural Network Techniques to Computer User Identification , 1997, Inf. Sci..

[12]  Kenneth Revett,et al.  Developing a keystroke dynamics based agent using rough sets , 2005 .

[13]  Arun Ross,et al.  An introduction to biometrics , 2008, ICPR 2008.

[14]  D. F. Specht,et al.  Probabilistic neural networks for classification, mapping, or associative memory , 1988, IEEE 1988 International Conference on Neural Networks.

[15]  E. Hernandez,et al.  User Authentication based on Human Typing Pattern with Artificial Neural Networks and Support Vector Machine , 2005 .

[16]  Allen Newell,et al.  The keystroke-level model for user performance time with interactive systems , 1980, CACM.

[17]  Michael K. Reiter,et al.  On User Choice in Graphical Password Schemes , 2004, USENIX Security Symposium.

[18]  Gopal K. Gupta,et al.  Identity authentication based on keystroke latencies , 1990, Commun. ACM.

[19]  Jan H. P. Eloff,et al.  Enhanced Password Authentication through Fuzzy Logic , 1997, IEEE Expert.

[20]  Fabian Monrose,et al.  Authentication via keystroke dynamics , 1997, CCS '97.

[21]  Sungzoon Cho,et al.  GA SVM Wrapper Ensemble for Keystroke Dynamics Authentication , 2006, ICB.

[22]  Mohammad S. Obaidat,et al.  Verification of computer users using keystroke dynamics , 1997, IEEE Trans. Syst. Man Cybern. Part B.

[23]  Mohammad S. Obaidat,et al.  A Multilayer Neural Network System for Computer Access Security , 1994, IEEE Trans. Syst. Man Cybern. Syst..

[24]  Michael K. Reiter,et al.  Password hardening based on keystroke dynamics , 2002, International Journal of Information Security.

[25]  K. Revett,et al.  A Breast Cancer Diagnosis System: A Combined Approach Using Rough Sets and Probabilistic Neural Networks , 2005, EUROCON 2005 - The International Conference on "Computer as a Tool".

[26]  Michael K. Reiter,et al.  The Design and Analysis of Graphical Passwords , 1999, USENIX Security Symposium.

[27]  Pingzhi Fan,et al.  Novel Impostors Detection in Keystroke Dynamics by Support Vector Machine , 2004, PDCAT.

[28]  Doug Mahar,et al.  Optimizing digraph-latency based biometric typist verification systems: inter and intra typist differences in digraph latency distributions , 1995, Int. J. Hum. Comput. Stud..

[29]  Marcus Brown,et al.  User Identification via Keystroke Characteristics of Typed Names using Neural Networks , 1993, Int. J. Man Mach. Stud..