Improving keystroke dynamics authentication system via multiple feature fusion scheme

Abstract

This paper reports the performance and effect of diverse keystroke features combination on keystroke dynamic authentication system by using fusion scheme. First of all, four types of keystroke features are acquired from our collected dataset, later then transformed into similarity scores by the use of Gaussian Probability Density Function (GPD) and Direction Similarity Measure (DSM). Next, three fusion schemes are introduced to merge the scores pairing with six fusion rules. Result shows that the finest performance is obtained by the combination of both dwell time and flight time collectively. Finally, this experiment also investigates the effect of using larger dataset on performance, which turns out to be rather consistent. © 2012 IEEE

A changeable personal identification number‐based keystroke dynamics authentication system on smart phones

“…As the brief reviews in Section 2 were mentioned, Teh and colleagues' [24] research revealed that it would lead to the highest degree of discrimination when both the PR and RP times were regarded as keystroke dynamics of the users. Therefore, within the present study, based on the RP and PR times obtained in the enrollment phase, the CKD Table I.…”

“…In this work, the results of Teh and colleagues' [24] study is adopted for collecting the users' PR and RP times. Additionally, according to the suggestions of Campisi et al [20], users should enter the given numbers for five times.…”

“…According to the research results reported by Boechat et al [23], they mentioned that the statistical classifier has the following characteristics such as simplification, speed, low-burden calculation, and the accuracy of identification as others. In Teh and colleagues' study [24], they conducted the related work on a variety of keystroke dynamics and analyzed various combinations of the four traditional keystroke dynamics (i.e., PR, PP, RP, and RR). The outcomes of the study reveal that it would lead to the best degree of discrimination by means of taking the PR and RP times as the keystroke dynamics of the specific user.…”

Work in progress: A new approach of changeable password for keystroke dynamics authentication system on smart phones

“…zero to nine), in order to collect users' relative keystroke dynamics. In this work, the results of Teh et al's study [29] is adopted for collecting the users' PR and RP times. Additionally, according to the suggestions of Campisi et al [3], users should enter the given numbers for five times.…”

“…The traditional keystroke dynamics include PR (Press-Release), PP (Press-Press), RP (Release-Press), and RR (Release-Release): In Teh et al's study [29], they conducted the related work on a variety of keystroke dynamics and analyzed various combinations of the four keystroke times (i.e., PR, PP, RP, and RR). The outcomes of the study reveal that it would lead to the best degree of discrimination by means of taking the PR and RP times as the keystroke dynamics of the specific user.…”