News
Deep Learning Based Network Intrusion Detection System for Resource-Constrained Environments
Congratulations to Syed Rizvi and co-authors Mark Scanlon, Jimmy McGibney, and John Sheppard on the publication of Deep Learning Based Network Intrusion Detection System for Resource-Constrained Environments in The 13th EAI International Conference on Digital Forensics and Cyber Crime.
Co-authors: Mark Scanlon, Jimmy McGibney, and John Sheppard.
AI-generated summary of the contribution: This paper presents a deep learning-based network intrusion detection system (IDS) for resource-constrained environments. The proposed 1D-Dilated Causal Neural Network (1D-DCNN) model is employed for binary classification on two popular datasets, CIC-IDS2017 and CSE-CIC-IDS2018. The model’s architecture is designed to compensate for the max pooling layer, preventing information loss and expanding its receptive field to gather additional contextual data. The results show that the proposed model outperforms existing deep learning approaches in terms of accuracy, achieving a high precision with malicious attack detection rate accuracy of 99.7% for CIC-IDS2017 and 99.98% for CSE-CIC-IDS2018. The model’s efficiency and effectiveness make it suitable for resource-constrained environments.