Whale Swarm Optimization Algorithm (WSO) to implement an Efficient and Enhanced Deep Neural Network based IDS for Cloud Environments

Abstract

Currently, cloud computing has turned up into a predominant feature among the users in organizations and companies. The two chief problems encountered by cloud service providers and the corresponding clients are security and efficiency. Cloud based services involve security risks, as cloud computing acts as a simulated collection of resources offered in an open environment which is termed as Internet. One of the major challenges for both cloud service providers and cloud users is detection of intrusions and attacks caused by unauthorized users. Consequently it has become more vital to construct an effective detection system for intrusion, towards detecting suspicious happenings and intruders both internal and external to the CC framework through network traffic monitoring, despite the fact of maintaining performance and also quality of service. We propose a smart approach in this research work, applying whale swarm optimization algorithm (WSO) to automatically develop a Deep Neural Network (DNN) based Anomaly Network Intrusion Detection System (ANIDS). For the proposed system, the concept of reverse learning is initiated in the actual whale swarm optimization algorithm so as to achieve optimization. This approach boosts the capability of node search process and also the rate of speed of the global search procedure is increased. For the purpose of simulation and validation of the proposed system, CloudSim 4.0 simulator platform and Kyoto 2006+ dataset version 2015 are utilized. The attained results of experiments reveal that, in contrast to various customary and recent methodologies, the proposed IDS accomplishes better detection rate and lesser false positive rate.