A hybrid soft computing technique for intrusion detection in web and cloud environment

Abstract

Cloud computing environment contains important, essential, or confidential information; therefore, a security solution is needed to prevent this environment from potential attacks. In short, cloud computing has become one of the most sought after technologies in the field of information technology, and among the most dangerous threats. In this article, we propose a hybrid soft computing technique for intrusion detection in web and cloud environment (ST‐IDS). In ST‐IDS, we illustrate whale integrated slap swarm optimization algorithm for pre‐processing which remove the unwanted/repeated data's in dataset. We introduce new clustering technique based on modified tug‐of‐war optimization algorithm which groups the data in different segments. Then, we develop hybrid machine learning technique that is, capsule learning based neural network which categorize the attack in cloud environment. Finally, the proposed ST‐IDS technique can evaluate through standard open source datasets are KDD cup'99 and NSL‐KDD. The performance comparison of the proposed ST‐IDS technique using existing innovative technologies in terms of accuracy, precession, recall, specificity, F measure, false positive rate, and false negative rate.

Intrusion detection system in cloud computing by utilizing VTR-HLSTM based on deep learning

“…An IDS is a technology that monitors the network traffic and detects malicious traffic or any type of assault, as well as issues alarms [2]. Cloud computing (CC) technology allows users to access, store, and maintain their data in new and potentially easier ways [3], [4]. The client computing paradigm has inherent issues with security, privacy, service availability, and other problems [5].…”