Artificial Intelligence-Based Intrusion Detection Systems for Cloud and Internet of Things (IoT) Environments

Abstract

The exponentially increasing number of IoT devices and their corresponding cloud infrastructures increases the attack surface․ Classic rule-based schemes and cryptographic solutions are not well adapted to dynamic‚ heterogeneous‚ distributed‚ and resource-constrained IoT-cloud infrastructures․ Artificial intelligence (AI) based techniques such as machine learning (ML)‚ deep learning (DL) and federated learning (FL)‚ considered as a new model for intrusion detection systems (IDS) to assess the threats in real time and respond to the threats effectively in the dynamic environment․ This paper thoroughly reviews the state-of-the-art AI-based IDS in a layer-wise manner which consists of IoT and cloud stacks․ It categorizes popular cyber-attacks associated with each layer (perception‚ network‚ transport‚ processing and application) and correlate the attacks to machine learning classifiers (SVM‚ KNN‚ Random Forest‚ CNN‚ RNN/LSTM‚ Autoencoder) at shallow and deep learning levels․ The research incorporates federated IDS‚ graph neural networks‚ transformer architecture and explainable artificial intelligence as models of machine learning and further discusses prominent research issues (data scarcity‚ adversarial robustness‚ latency‚ transferability) and the future direction of next-generation IoT-cloud security․