Firewalls are core elements in network security. However, managing firewall rules, especially for enterprise networks, has become complex and error-prone. Firewall filtering rules have to be carefully written and organized in order to correctly implement the security policy. In addition, inserting or modifying a filtering rule requires to overcome and filter a range of special attacks or issues in network. In this paper, we present a machine learning based algorithm that filter Denial of Service (DoS) attacks in networks. This filtering algorithm has been designed by using a classification algorithm based on principal component and correlation based filters. We show good quality and performance of our algorithm experimentally by executing our algorithm on a several packet flow data sets.Firewalls are core elements in network security. However, managing firewall rules, especially for enterprise networks, has become complex and error-prone. Firewall filtering rules have to be carefully written and organized in order to correctly implement the security policy. In addition, inserting or modifying a filtering rule requires to overcome and filter a range of special attacks or issues in network. In this paper, we present a machine learning based algorithm that filter Denial of Service (DoS) attacks in networks. This filtering algorithm has been designed by using a classification algorithm based on principal component and correlation based filters. We show good quality and performance of our algorithm experimentally by executing our algorithm on a several packet flow data sets.