Real Time Network Intrusion Detection with Optimized Inference

Jayanthi Sayi Surya Ryali; Kaushik Venkata Vasantha Kumar Pentyala; Himavanth Sai Potturi; Purna Chandra Reddy Putta; V. Asis Marceline

Real Time Network Intrusion Detection with Optimized Inference

Author(s)	Mr. Jayanthi Sayi Surya Ryali, Mr. Kaushik Venkata Vasantha Kumar Pentyala, Mr. Himavanth Sai Potturi, Mr. Purna Chandra Reddy Putta, V. Asis Marceline
Country	India
Abstract	Intrusion Detection Systems (IDS) are essential for protecting modern networked environments against increasingly sophisticated cyber threats. Although machine learning techniques have improved detection capabilities, their deployment in real-time systems is often limited by inference latency and scalability constraints. This paper presents a deep learning-based IDS using a multilayer perceptron (MLP) trained on the NSL-KDD dataset, with emphasis on optimizing inference performance for practical deployment scenarios. To address deployment challenges, the trained model is exported to ONNX format and evaluated using multiple execution backends, including ONNX Runtime and TensorRT on both CPU and GPU platforms. Additionally, the model is deployed using the Triton Inference Server to assess performance in a production-oriented setting. The proposed pipeline enables a comprehensive comparison of latency and throughput across different inference frameworks. Experimental results show that optimized inference using TensorRT achieves up to 4.8 times reduction in latency compared to the baseline PyTorch implementation, while maintaining comparable classification performance. The findings demonstrate that deployment-aware optimization plays a crucial role in building efficient IDS solutions and provide insights into selecting appropriate inference strategies for low-latency, high-throughput environments.
Keywords	Intrusion Detection System (IDS), Deep Learning, Multilayer Perceptron (MLP), NSL-KDD, Model Optimization, ONNX Runtime, TensorRT, Triton Inference Server, Low-Latency Inference, Network Security.
Field	Computer > Artificial Intelligence / Simulation / Virtual Reality
Published In	Volume 8, Issue 3, May-June 2026
Published On	2026-05-05

View / Download PDF File

E-ISSN 2582-2160

doi

CrossRef DOI is assigned to each research paper published in our journal.

IJFMR DOI prefix is
10.36948/ijfmr

Downloads

Research Paper Format Copyright Permission Form and Undertaking Form Cover Page Vol 8 Isu 2 Cover Page Vol 8 Isu 1 Cover Page Vol 7 Isu 6

All research papers published on this website are licensed under Creative Commons Attribution-ShareAlike 4.0 International License, and all rights belong to their respective authors/researchers.

CC-BY-SA

About IJFMR 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		+91-9687-828-838	editor@ijfmr.com

International Journal For Multidisciplinary Research

A Widely Indexed Open Access Peer Reviewed Multidisciplinary Bi-monthly Scholarly International Journal

Real Time Network Intrusion Detection with Optimized Inference

Share this