Abstract: Traditional verification of the access to a computer system is single password. The drawback of the password is that it is easily given away. Therefore there are great security threats in the access to information and resource in the computer. In an effort to confront the threats, biometrics （such as fingerprints, keystroke dynamics, and so on） combined with the traditional verification methods may greatly increase the system security. In view of the fact that it is not necessary for the verification of keystroke dynamics to utilize the additional equipment and the realization is relatively cheap, after studying the past research on this issue, the keystroke verification based on support vector machines （SVM） is proposed in terms of SVM’s super performance in pattern recognition. Through experiments SVM is compared with BP, RBF, PNN, and LVQ, and the conclusion is that SVM is the best choice in keystroke identification and therefore there is extensive application prospect about keystroke verification.