1st year CDT student

点击翻译按钮获取中文摘要

This PhD research project focuses on enhancing the security and robustness ofAI/ML systems in robotics. As these technologies become integral to autonomous systems,they introduce vulnerabilities that adversaries can exploit, potentially compromising safetyand functionality. The research aims to identify and address security threats in applicationslike autonomous path planning, computer vision, and reinforcement learning.The study includes simulating adversarial attacks, such as brute-force attacks on path-planningalgorithms, to uncover weaknesses and environmental factors that may affect system integrity.By implementing these attacks on both simulated and real-world robotic platforms, the research seeks to understand the limitations of current AI/ML algorithms under adversarialconditions.A comprehensive security assessment will catalogue various AI/ML uses in robotics, prioritisingthose most at risk. The project will cyclically evaluate multiple AI/ML applications, usingadversarial machine learning methods to test and improve their robustness. This iterativeapproach ensures a detailed examination of vulnerabilities and the development of effectivecountermeasures.The ultimate goal is to create a robust security framework applicable to various robotic systems,ensuring safe and reliable operations across industries. This research addresses the critical needfor improved security in AI/ML applications, providing solutions that support the evolvinglandscape of robotics technology.