Keystroke Dynamic Authentication Using Combined MHR (Mean of Horner’s Rules) and Standard Deviation

Abstract

Keystroke Dynamic Authentication used a behavior to authenticate the user and one of biometric authentication. The behavior used a typing speed a character on the keyboard and every user had a unique behavior in typing. To improve classification between user and attacker of Keystroke Dynamic Authentication in this research, we proposed a combination of MHR (Mean of Horner’s Rules) and standard deviation. The results of this research showed that our proposed method gave a high accuracy (93.872%) than the previous method (75.388% and 75.156%). This research gave an opportunity to implemented in real login system because our method gave the best results with False Acceptance Rate (FAR) is 0.113. The user can be used as a simple password and ignore a worrying about an account hacking in the system.

Combined scaled manhattan distance and mean of horner’s rules for keystroke dynamic authentication

“…At present, passwords are one of the popular authentication methods [3][4][5]. Usually, the contents of the password used by the user contain a variety of information they have (or what they know), such as full name, date of birth to the name of his parents [6,7]. Passwords are a simple authentication method that is very easy to implement.…”

“…Keystroke Dynamic Authentication (KDA) is one of the right solutions in several previous problems. KDA is an authentication technique that utilizes the habit of typing someone as a login parameter from the user of a system [6,11,12]. The purpose of KDA is to increase the security of using passwords that have been widely used and handle various account security issues that are often broken into by irresponsible TELKOMNIKA Telecommun Comput El Control  Combined scaled manhattan distance and mean of horner's rules… (Didih Rizki Chandranegara) 771 users (hackers or attackers) [3,6].…”

“…KDA is one of the Biometric Authentication techniques. Biometric Authentication utilizes something unique from users such as the face, fingerprints, and habits (in this case KDA) [3,6,13]. And every person face, fingerprints, and habits can not be imitated by others (one of the habits is typing characters using the keyboard or KDA).…”

“…This differentiates KDA with another Biometric Authentication which using adding devices (such as face or fingerprints) [17]. Another advantage of KDA is that the characters used in the password do not have to utilize special characters, but can use the alphabet and numeric characters [6,15]. Because utilizes the KDA method, users who enter into the system will not realize that the system they are using has used the KDA method for their account security.…”

“…The use of averages is not suitable for this problem, so we propose the use of Mean of Horner's Rules (MHR) which can adapt to changes in values over time. Also, by using MHR on KDA, it can improve accuracy in the classification between attackers and users rather than using averages [6,15]. So in this research, we will do a combination of the Scaled Manhattan method and MHR to improve accuracy in the classification between attackers and users.…”