Deep Reinforcement Learning based Intrusion Detection System for Cloud Infrastructure

Intrusion Detection in cloud platform is a challenging problem due to its extensive usage and distributed nature that are constant targets of new and unknown attacks. Intrusion detection system (IDS) is responsible for monitoring and detecting malicious activities in any computing system or a network. However, most of the traditional cloud IDSs are vulnerable to novel attacks. Also, they are incapable of maintaining a balance between high accuracy and less false positive rate (FPR). In this paper, we propose a deep reinforcement learning-based adaptive cloud IDS architecture that addresses the above limitations and performs accurate detection and fine-grained classification of new and complex attacks. We have done extensive experimentation using the benchmark UNSW-NB15 dataset that shows better accuracy and less FPR compared to the state-of-the-art IDSs.