User Authentication using Keystroke Dynamics

Jyotsna Gaikwad, MET Institute of Engineering, Nashik; Bhagyashree Kulkarni ,MET Institute of Engineering, Nashik; Nikita Phadol ,MET Institute of Engineering, Nashik; Sneha Sarukte ,MET Institute of Engineering, Nashik

Biometric, Digraph, Infancy, Keystroke Dynamics, Neurons

There is need to secure sensitive data and computer systems from intruders while allowing ease of access for authenticating the user is one of the main problems in computer security. Traditionally, passwords have been the usual method for controlling access to computer systems but this approach has many inherent flaws. Keystroke dynamics is a biometric technique to recognize and an analysis of his/her typing patterns. In the experiment, we measure mean, standard deviation and median values of keystroke features such as latency, duration, digraph and their combinations and compare their performance. The latest trend in authenticating users is by using the potentiality of biometrics. Keystroke dynamics is a behavioral biometrics which captures the typing rhythms of users and then authenticates them based on the dynamics captured. In this paper, a detailed study on the evaluation of keystroke dynamics as a measure of authentication is carried out. This paper gives an insight from the infancy stage to the current work done on this domain which can be used by researchers working on this topic.
    Journal Papers [1] C. J. C. Burges, “A tutorial on support vector machines for pattern recognition,” Data Mining Knowl. Discovery, vol. 2, no. 2, pp. 121–167, Jun. 1998. [2] R. V. Yampolskiy and V. Govindaraju, “Behavioural biometrics: A survey and classification,” Int. J. Biometrics, vol. 1, no. 1, pp. 81–113, 2008. [3] S. P. Banerjee and D. L. Woodard, “Biometric authentication and identification using keystroke dynamics: A survey,” J. Pattern Recognit. Res., vol. 7, no. 1, pp. 116–139, 2012. [4] P. S. Dowland and S. M. Furnell, “A long-term trial of keystroke profiling using digraph, trigraph and keyword latencies,” in Proc. Secur. Protection Inf. Process. Syst., vol. 147. 2004, pp. 275–289. [5] J. V. Monaco, N. Bakelman, S, -H. Cha, and C. C. Tappert, “Developing a keystroke biometric system for continual authentication of computer users,” in Proc. Eur. Intell. Secur. Inform. Conf. (EISIC), Aug. 2012, pp. 210-216. [6] R. A. Bradley and M.E. Terry, “Rank anlysis of incomplete block designs: I. The method of paired comparisons,” Biometrika, vol. 39, nos. 3-4, pp. 324- 345, 1952. [7] P. Bours and S. Mondal, “Recent advances in user authentication using keystroke dynamics biometrics,” in Continuous Authentication With Keystroke Dynamics. Greece: Science Gate Publishing, 2015, pp. 14-58. [8] S. Bhatt and T. Santhanam, “Keystroke dynamics for biometric authentication—A survey,” in Proc. Int. Conf. Pattern Recognit., Inform. Mobile Eng. (PRIME), Feb. 2013, pp. 17–23. [9] H. Locklear et al., “Continuous authentication with cognition-centric text production and revision features,” in Proc. Int. Joint Conf. Biometrics (IJCB), Sep./Oct. 2014, pp. 1–8. [10] Y. Zhong, Y. Deng, and A. K. Jain, “Keystroke dynamics for user authentication,” in Proc. Conf. Comput. Vis. Pattern Recognit. Workshops (CVPRW), Jun. 2012, pp. 117–123. [11] D. Umphress and G. Williams, “Identity verification through keyboard characteristics,” Int. J. Man-Mach. Stud., vol. 23, no. 3, pp. 263–273, Sep. 1985. Books [12] C. M. Bishop, Neural Networks for Pattern Recognition. London, U.K.: Oxford Univ. Press, 1995. Theses [13] S. Mondal, “Continuous user authentication and identification: Combination of security & forensics,” Ph.D. dissertation, Faculty Comput. Sci. Media Technol., Norwegian Univ. Sci. Technol., Trondheim, Norway, Feb. 2016. Proceedings Papers [14] Soumik Mondal and Patrick Bours, Person Identification by Keystroke Dynamics Using Pairwise User Coupling, vol. 12, no. 6, June 2017.
Paper ID: GRDJEV03I060036
Published in: Volume : 3, Issue : 6
Publication Date: 2018-06-01
Page(s): 58 - 66