Enhanced cloud security: a novel intrusion detection system using ARSO algorithm and Bi-LSTM classifier

The cloud computing environment faces significant security challenges, impacting its long-term growth. Intrusion detection is crucial for mitigating potential threats in this domain. However, due to the complexity and scale of network traffic, developing effective cloud intrusion detection systems (IDS) is challenging. Therefore, in this study we present a cloud-based IDS based on Adaptive Rat Swarm Optimization (ARSO) Algorithm and Bidirectional Long Short Term Memory (Bi-LSTM) classifier. The developed model comprises preprocessing, feature selection, and classification stages. Initially, data undergo preprocessing, followed by the selection of significant features using an Adaptive Rat Swarm Optimization (ARSO) Algorithm. The selected features are then fed into the Bi-LSTM classifier to classify packets as normal or abnormal. Experimental evaluation is conducted using the NSL-KDD dataset, comparing the performance of our approach with other state-of-the-art methods. Several criteria are employed to assess the efficacy of our suggested approach. The results demonstrate that the proposed strategy achieves superior classification efficiency than other state-of-the-art techniques.