A Survey for Deep Reinforcement Learning Based Network Intrusion Detection

A research paper surveys the application of deep reinforcement learning (DRL) to network intrusion detection systems, finding that while DRL shows promise and occasionally outperforms traditional methods, many technologies remain underexplored. The study identifies key challenges including training efficiency, minority attack detection, and dataset imbalances, while proposing integration with generative methods for improved performance.

• →Deep reinforcement learning models occasionally achieve state-of-the-art results on public datasets, outperforming traditional deep learning methods for intrusion detection.
• →Key challenges include model training efficiency, detection of minority and unknown class attacks, feature selection, and handling unbalanced datasets.
• →Many recent DRL technologies remain underexplored in network intrusion detection applications.
• →The research recommends focusing on Internet of Things intrusion detection for real-world deployment and testing.
• →Integration of DRL with generative methods is proposed to address current gaps and improve system robustness.