Abstract: The purpose of intrusion detection is to identify an unauthorized use, misuse and damage to computer systems and networks by either of two internal users and external attackers. In this study, we have presented a new approach based on machine learning techniques to identify malicious attacks and provide security at an accessible level for users. The introduced method uses a genetic algorithm with a statistical target function based on the data distribution to select the features and the support vector machine for classification. The results of the simulation proposed good quality of the indicative method.