基于击键特征的智能手机身份认证方法

With the development of brute force attacks, smudge attacks and user information disclosure, PIN-based mobile identity authentication system is no longer safe and secure. Therefore, a smartphone authentication method based on keystroke dynamics is proposed in this paper. This method extracts second-order keystroke features which are more stable and reliable from the first-order keystroke as the experimental features. Based on the SMOTE and Tomek Links algorithms, a classification algorithm that can solve data imbalance is implemented. The experimental results show that this method solves the problem of data imbalance and has a high user identification rate, which can effectively improve the security of the PIN authentication system.