10-04-2017, 08:45 PM
[attachment=7599]
Abstract-
As the Pc s and LAN s came to existence security became the major issue. Then passwords and smart cards came into existence for providing security and well worked for a period of time without getting hacked. As a result passwords are not enough which has to be replaced by some unique factor of authentication & identification which can serve well than passwords and smart cards which lead to the era of biometrics.
This paper provides an introduction to biometric security using keystroke analysis. Here as follows we go into the topic .Typing rhythms are one of the rawest forms of data stemming from the interaction between humans and computers. So why can t we jutilise this data for personal identity? Keystroke analysis uses manner and rhythm in which user types input using keyboard. Digraph latency plays a prominent role and recorded for the future authentication as the method is based on typing rhythm. As typing rhythms is a part of behavioural biometrics and its uniqueness makes it security at the top with top security
Keywords- Dwell time, Flight time, Digraph latency.
I. INTRODUCTION
Keystroke analysis is the user s identity through their way of typing on a computer keyboard. Typed key measurements available from most every keyboard can be recorded to determine Dwell time (The time a key pressed) and Flight time (The time between key down and the next key down ). The recorded keystroke timing data is processed through a unique neural algorithm, which determines a primary pattern for the future comparisons. The neural algorithm is provided with Digraph latencies (The elapsed time between the release of the first key and the depression of the second key). The extractions of such features are accepted from the free text provided for the user to create his own profile. Keystroke is a pure software solution. The only required hardware is the standard keyboard that comes with every computer. The system does not require sensors or other additional hardware. Keystroke analysis can completely replace password procedure on the Internet. Users do not have to remember a password. It is highly secure because keystroke behaviour cannot be imitated, stolen, forgotten or misplaced. The assertion that a person's keystroke behavior is exactly as unique as their fingerprint was borne out by scientific research at the University of Regensburg. It is possible to identify a user through the way he types on a keyboard even when the user is entering free text in a language different for the one he used to form his recognition profile. Intrusion detection system has an accuracy of limiting the False alarms . The system will not be fooled by the typing rhythms of a language different from the one of the user s profiles used by the intruders. By this we can say that the keystroke analysis can be used to ascertain personal identity