An intelligent intrusion detection system for secure wireless communication using IPSO and negative selection classifier

Internet security is very crucial need in this real world environment due to the rise of e-business, e-learning, and e-governance. Intellectual data mining applications are useful for producing security while accessing through the internet from cloud databases. Currently, the cloud security researchers are not in a position to introduce more reliable, secure and effective real-time intrusion detection systems for detecting the intruders in online. For fulfilling this requirement, we propose a new intelligent classification model for anomaly detection which detects the intruders effectively in cloud networks using a combination of an enhanced incremental particle swarm optimization and negative selection algorithm. Moreover, we enhanced these two methods by the uses of Minkowski distance metric for effective decision making. The experimental results of the proposed classification model show that this system detects anomalies with low false alarm rate and high detection rate when tested with NSL-KDD dataset which is modified from KDD 1999 Cup dataset.