Application of a Dynamic Identity Authentication Model Based on an Improved Keystroke Rhythm Algorithm

Abstract

Keystroke rhythm identification, which extracts biometric characteristics through keyboards without additional expensive devices, is a kind of biometric identification technology. The paper proposes a dynamic identity authentication model based on the improved keystroke rhythm algorithm in Rick Joyce model and implement this model in a mobile phone system. The experimental results show that comparing with the original model, the false alarm rate (FAR) of the improved model decreases a lot in the mobile phone system, and its growth of imposter pass rate (IPR) is slower than the Rick Joyce model's. The improved model is more suitable for small memory systems, and it has better performance in security and dynamic adaptation. This improved model has good application value.

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

“…This research uses a method from Yang and Fang [6] which was improved research from Joyce and Gupta classification methods [5]. The proposed method is replacing the average use with MHR (mean of Horner's Rule).…”

“…Based on this statement [1], this research was improved research using the proposed method i.e. MHR and classification methods by [6]. The Equation 1 used in the classification of KDA by Joyce and Gupta [5] is:…”

“…This research aims to improve the accuracy of previous researches, i.e. Gupta & Gopal [5] and Yang & Fang [6]. Researches [5] [6] used the average for the KDA classification.…”

“…Gupta & Gopal [5] and Yang & Fang [6]. Researches [5] [6] used the average for the KDA classification. The use of average according to Ho and Kang [1] research is not suitable for data streams such as KDA, so it is proposed to use the mean of Horner's Rule (MHR) that is suitable for data streams.…”

“…The use of average according to Ho and Kang [1] research is not suitable for data streams such as KDA, so it is proposed to use the mean of Horner's Rule (MHR) that is suitable for data streams. Based on [1], this research proposed to use MHR for the classification of KDA and combined it with a method that was used by Gupta & Gopal [5] and Yang & Fang [6]. An explanation of the method used will be presented in the Research Method and continued with the Results and Discussion of the results of the research that has been carried out.…”