Comparative Study of Classification Algorithms for Cloud IDS using NSL-KDD Dataset in WEKA

Cloud based Intrusion Detection Systems (IDS) presented an effective way to increase the detection rates of malicious activities in the past couple of years. However, the implementation of these systems using traditional techniques is a herculean task due to the exponential growth of network bandwidth with the very limited availability of computational resources. One topic that intuitively stands out as a potential for solving this issue is Artificial Intelligence (AI). In this paper, we present an overview of recent detection proposals in the field of security intrusion detection using the contributions of new trends in AI (Artificial Intelligence) with an experiment carried out to evaluate the performance of different machine learning techniques using the most used dataset in information security research NSL-KDD and its various components in WEKA. Results show that the best classification algorithm is Random Forest with a Precision of 98.6%.