Keystroke statistical learning model for web authentication

Keystroke typing characteristics is considered as one of the important biometric features that can be used to protect users against malicious attacks. In this paper we propose a statistical model for web authentication with keystroke typing characteristics based on Hidden Markov Model and Gaussian Modeling from Statistical Learning Theory. Our proposed model can substantially enhance the accuracy of the identity authentication by analyzing keystroke timing information of the username and password. Results of the experiments showed that our scheme achieved by far the best error rate of 2.54 %. Keywords Keystroke, Statistical Learning Theory, Hidden Markov Model, web authentication, Gaussian Model

• Type: Conference
• Year: 2007
• Where: CCS
• Authors: Cheng-Huang Jiang, Shiuhpyng Shieh, Jen-Chien Liu
• Keywords: CCS 2007, Hidden Markov Model, Keystroke Typing Characteristics, Security Privacy, Statistical Learning Theory