Security Analysis in Cloud Environment

Abstract

Cloud computing is a new environment similar to distributed systems and is limited to its use of networking. Therefore, security issues are prevalent and cannot be ignored. Intrusion detection systems (IDS) are used to detect malicious behavior in network communication and hosts in real time. An open-source IDS widely in use is Snort, powerful IDS that can be configured by writing simple rules to detect a wide variety of hostile or suspicious network traffic. But IDS alone cannot effectively analyze the security threats as they have high rates of false alerts. Several machine learning and neural network algorithms have been tested on available datasets, and it has been proved that these algorithms help reduce false alerts up to a large extent. In this paper, we propose a way to bridge the gap between intrusion detection system benchmarking and real-world attacks by making use of effective and efficient algorithms.