A personalized rhythm click‐based authentication system

Abstract

Purpose -In keystroke-based authentication systems, an input device to enter a password is needed. Users are verified by checking the validity of the password and typing characteristics. However, some devices have no standard desktop keyboard such as personal digital assistants and mobile phones. With these types of electronics, the system cannot successfully work in the authentication phase while the registration process is implemented based on a computer keyboard. This results in a reduction of system portability. The purpose of this paper is to employ the rhythm clicked by a mouse as another identifiable factor to authenticate a user's identity. Design/methodology/approach -Mouse click can be replaced by a stylus and fingers on touch screens or numeral buttons on mobile phones. A total of 25 users participated and the click data are based on time instances of pressing and releasing the mouse button, which are captured while the user clicks a rhythm. Three features are calculated using these click data, and a reasonable amount of results with neural networks and other classifiers shows the click characteristics are able to function as another identifiable factor. Findings -A reasonable amount of results with neural networks and other classifiers shows the click characteristics are able to function as another identifiable factor. Originality/value -The paper presents a personalized rhythm click-based authentication system.

Two novel biometric features in keystroke dynamics authentication systems for touch screen devices

“…In the enrollment phase, a user is asked to register his/her password, and the corresponding keystroke features are recorded. Most KDA systems are used in alphanumeric‐based passwords for QWERTY keyboards . In the related literatures, a user's keystroke feature samples consist of keystroke time features such as a keystroke duration time [i.e.…”

“…Therefore, Chang et al . employed a personal music rhythm on the basis of the user's uniqueness and consistency rather than the artificial rhythm. Users use a mouse to click their personal music rhythm directly.…”

“…Chang et al . used the mouse to simulate users clicking on the touch panel, respectively. However, the experiment of Saevanee et al .…”

Implementing multiple biometric features for a recall-based graphical keystroke dynamics authentication system on a smart phone

“…Nauman and Ali [29] indicated that the adoption of text-based password on mobile devices would make the user choose simple passwords with lower security. For adopting KDA on a smart phone with a smaller screen, Chang et al [8] asked users to click the mouse in order to simulate the behavior of touch screen clicking. The personalized click feature samples generated by the mouse-clicking event were collected.…”

“…After that, we investigated the authentication utility for adopting 5,6,7,8,9, and 10 training samples. Adopting five training samples meant that the 1 st to 5 th samples were chosen as the training samples, and likewise, 6 training samples meant the 1 st to 6 th samples were selected for classifier training and so on.…”