Defending Denial of Service Attacks against Domain Name System with Machine Learning Techniques

Along with the explosive growth of the Internet, the demand for efficient and secure Internet Infrastructure has been increasing. For the entire chain of Internet connectivity the Domain Name System (DNS) provides name to address mapping services. Hackers exploit this fact to damage different parts of Internet. This paper focuses on Denial of Service (DoS) attacks as the major security issue during recent years. The process of detection and classification of DoS against DNS has been presented in two phases in our model. The proposed system architecture consists of a statistical pre-processor and a machine learning engine. Three different types of neural network classifiers and support vector machines are evaluated as the engine in a simulated network. The performance of our system was measured in terms of detection rate, accuracy, and false alarm rate. The results indicated that a back propagation neural network provides a 99% accuracy and an acceptable false alarm rate of 0.28% comparing to other types of classifiers.