An Implicit Identity Authentication System Considering Changes of Gesture Based on Keystroke Behaviors

Smartphones have become ubiquitous personal devices so that much of sensitive and private information will be saved in the phone, and users have their own unique behavioral characteristics when using smartphones, so, to prevent private information from falling into the hands of impostors, there is a kind of identity authentication system based on user's behavioral features while the user is unlocking. However, due to the impact of environmental factors, changes of gesture will introduce bias into the feature data, which results in a diminishment of the system performance. To solve this problem, we propose an implicit identity authentication system based on keystroke behaviors, and it is the first attempt to consider the changes of a user's gesture. This system collects five keystroke features in the background and analyzes to identify different users without additional hardware supporting. We present our work with an experimental study, and our experiments show that the accuracy of identity authentication system we proposed is up to 99.1329%. Comparing with the identity authentication system without considering the impact of gesture changes, the EER of the system considering the impact of gesture changes is decreased by 1.2514%.