A Case Study on Using Deep Learning for Network Intrusion Detection
This is an incremental study applying existing deep learning methods to network security, potentially benefiting cybersecurity professionals.
The paper tackled the problem of applying deep learning to network intrusion detection, showing that Deep Neural Networks outperform other machine learning systems and are robust to dynamic IP addresses, and that Autoencoders are effective for anomaly detection.
Deep Learning has been very successful in many application domains. However, its usefulness in the context of network intrusion detection has not been systematically investigated. In this paper, we report a case study on using deep learning for both supervised network intrusion detection and unsupervised network anomaly detection. We show that Deep Neural Networks (DNNs) can outperform other machine learning based intrusion detection systems, while being robust in the presence of dynamic IP addresses. We also show that Autoencoders can be effective for network anomaly detection.