Hybrid CNN–LSTM Architecture for Multi-Class Network Intrusion Detection with GPU Acceleration

Author(s)	Kartikeya Kumar, Dr. Sunil Kumar Sharma
Country	India
Abstract	Network intrusion detection systems (NIDS) play a critical role in contemporary cybersecurity systems. The traditional systems however have the problems of high false positives, failure to detect the zero day attacks, and low scalability when the network is under high throughput conditions. To overcome these limitations, this thesis is based on a hybrid deep learning architecture, which combines Convolutional Neural Networks (CNNs) and Long Short-Term Memory (LSTM) networks. This proposed model can be optimized with the help of both the acceleration of the use of GPU and mixed-precision training in order to efficiently work with the data in the traffic of the network of great sizes. This is proven by the results of extensive experiments on a real-world dataset of more than 2.5 million network flows of seven attack types, which indicates that the proposed approach can be used to obtain strong detection results and it remains computationally efficient. The findings confirm the applicability of lightweight hybrid architectures in real-time and resource constrained deployment environments.
Keywords	Network Intrusion Detection, Deep Learning, CNN-LSTM, GPU Acceleration, Class Im- balance, Mixed Precision Training.
Field	Computer Applications
Published In	Volume 7, Issue 2, March-April 2026
Published On	2026-04-11

About AIJFR Fees & Payment Current Issue Publication Archive	Submit Research Paper Track Submission Status Publication Guidelines Publication Ethics Peer Review & Plagiarism	Join as a Reviewer Editors & Reviewers Reviewer Referral Program Get Reviewer Membership Certi.	Website/Journal Policies Usage Policy Content Policies Privacy Policy

Contact Us		+91-9898-79-39-59	editor@aijfr.com

Advanced International Journal for Research