Machine Learning for Cyber-Attack Identification from Traffic Flows

Yujing Zhou, Marc L. Jacquet, Robel Dawit, Skyler Fabre, Dev Sarawat +7 more
5/2/2025
cs.LGcs.CR

No official code found. Best implementation: U1overground/Cybersummer (0 stars, last commit 2025-03-28).

Abstract

This paper presents our simulation of cyber-attacks and detection strategies on the traffic control system in Daytona Beach, FL. using Raspberry Pi virtual machines and the OPNSense firewall, along with traffic dynamics from SUMO and exploitation via the Metasploit framework. We try to answer the research questions: are we able to identify cyber attacks by only analyzing traffic flow patterns. In this research, the cyber attacks are focused particularly when lights are randomly turned all green or red at busy intersections by adversarial attackers. Despite challenges stemming from imbalanced data and overlapping traffic patterns, our best model shows 85\% accuracy when detecting intrusions purely using traffic flow statistics. Key indicators for successful detection included occupancy, jam length, and halting durations.

View on arXivView PDF

Code Implementations(1)

U1overground/CybersummerCommunity100%
00Jupyter NotebookMar 28, 20251 years ago

Similar Papers

Explainable Machine Learning for Cyberattack Identification from Traffic Flows

88% match1 repo2025

Revisiting Network Traffic Analysis: Compatible network flows for ML models

82% match2025

Reliable Feature Selection for Adversarially Robust Cyber-Attack Detection

82% match2024

Using Graph Theory for Improving Machine Learning-based Detection of Cyber Attacks

82% match2024

Intrusion Detection in Internet of Vehicles Using Machine Learning

81% match2025

A Comparative Analysis of Machine Learning Models for DDoS Detection in IoT Networks

81% match2024

Cite this paper

@article{zhou2025machine,
  title  = {Machine Learning for Cyber-Attack Identification from Traffic Flows},
  author = {Yujing Zhou and Marc L. Jacquet and Robel Dawit and Skyler Fabre and Dev Sarawat and Faheem Khan and Madison Newell and Yongxin Liu and Dahai Liu and Hongyun Chen and Jian Wang and Huihui Wang},
  year   = {2025},
  eprint = {2505.01489},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2505.01489v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2505.01489.svg)](https://codeofpaper.com/paper/2505.01489)

Discussion