Hybrid Deep (CNN-BiLSTM) Intrusion Detection for Defense and Mission-Critical Networks

Authors

• Corey A Cheng, University at Albany, SUNYFollow
• Jermaine Anim-Addo, University at Albany, SUNYFollow
• Asma Jakir Hussain, University at Albany, SUNYFollow
• Zion O Smith-Fox, University at Albany, SUNYFollow
• Sanjay Goel, University at Albany, SUNYFollow
• Yuksel Celik, University at Albany, State University of New YorkFollow

Abstract

This article examines how hybrid deep learning can strengthen intrusion detection for military and defense networks. Using the CSE-CIC-IDS2018 dataset, the study evaluates a CNN-BiLSTM model designed to detect benign traffic and multiple attack categories, including DDoS, DoS, botnet, brute-force, web attack, and infiltration activity. The model achieved strong multi-class detection performance, with 0.9893 accuracy and 0.9979 ROC-AUC. The findings suggest that AI-supported intrusion detection can improve cyber defense operations, analyst triage, and protection of mission-critical networks.

DOI

https://doi.org/10.5038/2378-0789.9.1.1157

Recommended Citation

Cheng, Corey A; Anim-Addo, Jermaine; Jakir Hussain, Asma; Smith-Fox, Zion O; Goel, Sanjay; and Celik, Yuksel (2026) "Hybrid Deep (CNN-BiLSTM) Intrusion Detection for Defense and Mission-Critical Networks," Military Cyber Affairs: Vol. 9 : Iss. 1 , Article 8.
https://doi.org/10.5038/2378-0789.9.1.1157
Available at: https://digitalcommons.usf.edu/mca/vol9/iss1/8