Intrusion Detection System for AD in IoT Stochastic Mean Fusion Using Red-Tailed Hawk Algorithm

In Internet of Things (IoT), an Intrusion Detection Systems (IDS) for AD by monitor network traffic and device behaviour to recognize unusual patterns that indicate security threats. They help protect IoT networks by detecting deviations from normal operations, potentially preventing cyberattacks. However, the proliferation of IoT devices has made networks increasingly vulnerable to cyber threats, posing challenges in identifying anomalous behaviours within large-scale environments. Developing an effective IDS for AD in IoT is critical to addressing evolving security threats and ensuring reliable performance. To overcome these challenges, a model based on DL (DL) and metaheuristic optimization algorithm is proposed for robust classification and feature selection. The proposed Stopshatic Mean Fusion - Red-Tailed Hawk (SMF-RTH) approach is utilized to detect anomalies in large-scale IoT systems and address security threats effectively. A simple yet effective SMF-RTH is applied as a feature selector to enable the model to learn more accurate and appropriate representations of input data in a lower-dimensional space. In the classification phase, Long Short-Term Memory (LSTM) is employed to detected an anomaly. The proposed method achieves an accuracy of 99.7% and 99.2% on the CICIDS 2017 and KDD-Cup 99 datasets, respectively.