作者: Romain Giot , Mohamad El-Abed , Christophe Rosenberger
关键词:
摘要: Most keystroke dynamics studies have been evaluated using a specific kind of dataset in which users type an imposed login and password. Moreover, these are optimistics since most them use different acquisition protocols, private datasets, controlled environment, etc. In order to enhance the accuracy dynamics' performance, main contribution this paper is twofold. First, we provide new typed both chosen pairs logins passwords. addition, samples collected web-based uncontrolled environment (OS, keyboards, browser, etc.). Such important it provides us more realistic results performance comparison literature (controlled Second, present statistical analysis well known assertions such as relationship between password size, impact fusion schemes on system overall others entropy. We put into obviousness some conditions.