Keystroke Dynamics

This research is being led by Shimon Modi and Narainsamy Pavaday

There are a number of research activities that are underway in the biometrics lab relating to research in keystroke dynamics.

The first project is to establish a static based password verification methodology through the use of predictive strength of typing patterns.
The second project is to estimate the reliability on computer based timers for keystroke dynamics.
The third project is to present a novel approach to authenticating users of static password systems through the application of contour map pattern-matching techniques. We propose an autogenic learning mechanism that can be linked with the authenticated users’ unique and individual keystroke dynamics. These combined data can be used to discriminate between authenticated users and impostors. By executing a prototype of our plan, we want to test the approach's practical viability in terms of results, ease of implementation and application.

Previous Research

Keystroke dynamics is a concept to address the inherent weakness of knowledge-based passwords. Current keystroke dynamics solutions work with static passwords. This concept adds a layer of security to password protection, but the user is still obligated to remember their password. The password protection scheme is less vulnerable, but it is not inviolable. Keystroke dynamics is the only behavioral biometric that works as a software-based solution and does not require additional hardware other than what accompanies a regular computer. In the past, research in the field of keystroke dynamics has focused on static verification. There is no argument that static verification reduces the success rate of an imposter gaining unauthorized access under the genuine identity, but the problem authorized users forgetting their passwords persists. A keystroke dynamics solution that does not require users to remember their passwords would be a better option for commercial and business users than currently commercially available keystroke dynamics solutions. Research has been conducted into examining use of spontaneously generated passwords as a means of replacing knowledge based password, but still incorporating the strength of keystroke dynamics. For more information please contact Shimon Modi.

Previous Work and Publications

	Modi*, S. K., & Elliott, S. J. (2006). Keystroke Dynamics Verification Using Spontaneously Generated Password. Paper presented at the 40th IEEE International Carnahan Conferences Security Technology, Lexington, Kentucky.
	Modi, S. K. (2005). Keystroke Dynamics Verification Using Spontaneous Password. Purdue University, West Lafayette.