User Authentication process is the essential integral part of any secure or collaborative system. Where, Knowledge-based Authentication is convenient and low cost among currently used authentication processes. But, today, password or PIN is not limited in knowledge-based user authentication due to off-line guessing attacks; it demands higher level of security and performance together with low cost. Here, Keystroke Dynamics is the best possible solution, where the users are not only indentified by their password or PIN, their regular typing style is also accounted for. But this technique, as is now, suffers from accuracy level and performance. Thus, in order to realize this technique in practice a higher level of security and performance together with low cost version is demanded with an error to an accepted level. Hence, it is highly needed to identify the controlling parameters and optimize the accuracy and performance. In this paper we investigated typing style of 15 different individuals with 3 different texts and analyzed the collected data. Here, we introduced some effective factors which can optimize the accuracy and performance and at the end, we concluded by suggesting some future plans that also can be effectively implemented by this technique.

Keystroke Dynamics, Behavioral biometric, Computer Security, Manhattan Distance, Euclidean Distance, Mahanobolis Distance, Z Score, EER, FAR, FRR, Knowledge-based Authentication

[1] Hafiz, Z. U. K. (2010). Comparative Study of Authentication Techniques. International Journal of Video & Image Processing and Network Security, IJVIPNSIJENS Vol: 10, No: 04.
[2] Gaines, R. et al. (1980). Authentication by keystroke timing: some preliminary results. Rand Rep. R-2560-NSF, Rand Corporation.
[3] Bleha, S. et al. (1990). Computer-access security systems using keystroke dynamics. IEEE Transactions on Pattern Analysis and Machine Intelligence 12, 1217–1222.
[4] Killourhy, K. S. (2012). A Scientific Understanding of Keystroke Dynamics. PhD thesis, Computer Science Department, Carnegie Mellon University, Pittsburgh, US.
[5] Joyce, R. & Gupta, G. (1990). Identity authorization based on keystroke latencies. Communication of ACM 33 (2) 168–176.
[6] Monrose, F. & Rubin, A. D. (2000). Keystroke dynamics as a biometric for authentication. Future Generation Computer Systems, Vol. 16, No. 4, pp. 351–359.
[7] Shimaa, I. H. et al. (2013). User Authentication with Adaptive Keystroke Dynamics. IJCSI, Vol. 10, Issue 4, July 2013.
[8] Pin, S. T. (2013). A Survey of Keystroke Dynamics Biometrics. The Scientific World Journal, Vol-2013, Article ID 408280.
[9] Giot, R. et al. (2011). Analysis of template updates strategies for keystroke dynamics. Computational Intelligence in Biometrics and Identity Management (CIBIM), 2011 IEEE Workshop, pp.21,28, 11-15.