Evaluating the Impact of Denial-of-Service (DoS) Attacks on Enterprise Networks Using Optimized Network Engineering Tools (OPNET 14.5) and Machine Learning - A Research Article

Aug 4, 2026

Upload by Riley

The research evaluates enterprise network performance under Denial-of-Service (DoS) attacks using machine learning models and OPNET 14.5 simulation. Service interruptions and financial losses stem from DoS attacks that substantially degrade network performance. Traditional defenses often fail to provide real-time detection and response, leaving enterprises vulnerable to recurring attack patterns. Simulation experiments assess latency and throughput with packet loss statistics across multiple DoS scenarios, while decision trees and support vector machines identify normal versus attack traffic.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages11

Reading Time28 min

AccessFree to download

Introduction

Background and Motivation

Related Work and Threat Evolution

Research Objective and Approach

| International Journal of Scientific Research in
Network Security and Communication
Vol.13, Issue.2, pp.01-11, April 2025
ISSN: 2321-3256 (Online)
Available online [at: www.ijsrnsc.org](at: www.ijsrnsc.org) | | | | --- | --- | --- | | Research Article
Evaluating the Impact of Denial-of-Service (DoS) Attacks on Enterprise Networks Using Optimized Network Engineering Tools (OPNET 14.5) and Machine Learning
Ojo Jayeola Adaramola1*, Olaniyi Habib Aliu2
1Dept. of Computer Engineering, School of Engineering, Federal polytechnic Ilaro, Ogun State, Nigeria 2Dept. of Computer Engineering, School of Engineering, Federal polytechnic Ilaro, Ogun State, Nigeria
*Corresponding Author: ✉ Tel.: +234 703 273 0955
Received: 01/Apr/2024, Accepted: 15/Apr/2025, Published: 30/Apr/2025| DOI: [https://doi.org/10.26438/ijsrnsc.v13i2.271](https://doi.org/10.26438/ijsrnsc.v13i2.271) | | | | | Copyright © 2025 by author(s). This is an Open Access article distributed under the terms of the Creative Commons Attribution 4.0 International License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited & its authors credited. | | | Abstract—The research conducts a network performance analysis of enterprise systems under Denial-of-Service (DoS) attacks through machine learning modeling with OPNET 14.5. Service interruptions along with financial losses result from Denial-ofService attacks which seriously reduce network performance. The implementation of multiple defense measures has not resolved the persistent problem with real-time detection and response for enterprises. Through OPNET 14.5 simulation the research evaluates multiple DoS attack situations alongside their effects on performance metrics by measuring latency and achieving throughput and packet loss statistics. Two machine learning models with decision trees and support vector machines serve to detect normal and attack-related traffic patterns. The simulation demonstrates that networks experience severe degradation when under DoS attacks which leads to longer delays and packet drops. The machine learning detection systems show excellent attack pattern recognition abilities which indicates their practical use in preventing attacks. The authors suggest security frameworks should implement machine learning detection systems as part of their enterprise security infrastructure for better DoS protection. The research provides final proof about integrating network simulation along with machine learning technologies to stop DoS attacks which will enable further cybersecurity defense system development.
Keywords—Denial-of-Service (DoS), Enterprise Security, Network Performance, Machine Learning, OPNET | | | 1. Introduction Enterprise networks experience vital cybersecurity dangers throughout digital development since organizations elevate their dependence on connected systems. Organization networks face their most important security threat from Denial-of-Service (DoS) attacks which disrupt services through massive network resource exhaustion [1] . These assaults generate business stoppages and monetary losses accompanied by deteriorating brand reputation. Future iterations of cyber threats require organizations to enhance their capabilities of detecting and evaluating and mitigating DoS attacks because of their increasing occurrence. According to [2], DoS attacks began during the first internet period by sending numerous excessive requests to capitalizing on server capacity issues [3] [4] . Attack techniques have progressed since the beginning of the internet by adding UDP and SYN flooding and application-layer assault vectors to their repertoire. The increased capability of Botnets due to their ability to control enormous collections of compromised devices now creates added complexity to prevent DoS attacks according to [5] . [6], identify an ongoing cybersecurity issue because of the execution an

FAQs

How does the study evaluate DoS attack impact on enterprise networks?

It uses OPNET 14.5 simulation to model multiple DoS scenarios and measures performance metrics including latency, throughput, and packet loss statistics.

Which machine learning models are used for detecting DoS traffic patterns?

Two models are applied: decision trees and support vector machines, trained to distinguish normal traffic from attack-related traffic.

What do the results indicate about network behavior during DoS attacks?

The study shows severe degradation, leading to longer delays and increased packet drops, while the machine learning detection systems demonstrate strong recognition of attack patterns.

Aug 4, 2026

Upload by Riley