Abstract :

The Increasing Adoption Of Robotic Systems In Domains Such As Healthcare, Manufacturing, And Autonomous Vehicles Has Led To The Widespread Use Of The Robot Operating System (ROS) As A Flexible Middleware Framework. However, ROS-based Systems Are Inherently Vulnerable To Various Cyber-attacks Due To Their Distributed Architecture, Lack Of Built-in Security Mechanisms, And Open Communication Protocols. Attacks Such As Node Spoofing, Message Tampering, Denial-of-service (DoS), And Unauthorized Access Can Compromise System Integrity And Safety. This Project Proposes An Intelligent Attack Detection System For ROS-based Environments Using Machine Learning Techniques To Enhance Security And Resilience. The Proposed System Monitors Communication Between ROS Nodes By Capturing Network Traffic And Message-level Data Such As Topics, Publishers, Subscribers, And Message Frequencies. Data Preprocessing Techniques Including Filtering, Normalization, And Feature Extraction Are Applied To Prepare The Dataset. Machine Learning Algorithms Such As Random Forest, Support Vector Machines (SVM), And Artificial Neural Networks (ANN) Are Used To Classify Normal And Malicious Activities. Additionally, Anomaly Detection Techniques Are Incorporated To Identify Unknown Or Zero-day Attacks That Are Not Present In The Training Data. Experimental Results Demonstrate That The Proposed System Effectively Detects Various Types Of Attacks With High Accuracy And Low False-positive Rates. Ensemble Models Such As Random Forest Show Strong Performance Due To Their Ability To Handle Complex Patterns In Network Behavior. The System Can Operate In Near Real-time, Making It Suitable For Securing Critical Robotic Applications. However, Challenges Such As Dataset Availability, Real-time Processing Overhead, And Evolving Attack Patterns Remain. Overall, The Proposed Solution Provides A Scalable And Intelligent Approach To Enhancing The Security Of ROS-based Systems.

Published:

08-4-2026

Issue:

Vol. 26 No. 4 (2026)

Page Nos:

1844-1850

Section:

Articles

License:

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

How to Cite