Asynchronous Fault Detection for Unmanned Marine Vehicles Under Deception attacks
TL;DR: This paper addresses the challenge of thruster fault detection in Unmanned Marine Vehicles (UMVs) subjected to deception attacks, a sophisticated type of cyber threat where adversaries manipulate sensor data to mislead fault detection systems.
Abstract: This paper addresses the challenge of thruster fault detection in Unmanned Marine Vehicles (UMVs) subjected to deception attacks, a sophisticated type of cyber threat where adversaries manipulate sensor data to mislead fault detection systems. Deception attacks pose significant risks by introducing erroneous data, which can obscure genuine faults and disrupt the reliability of detection mechanisms. To tackle this issue, the study proposes a novel detection framework that integrates an advanced asynchronous switched filter designed specifically to counteract the effects of deception attacks. This approach combines adaptive filtering techniques with robust model-based methods to enhance the accuracy and reliability of fault detection. The framework employs model-dependent average dwell time (MDADT) and piecewise Lyapunov functions (PLF) to derive rigorous conditions that ensure global stability and optimal performance under the influence of deceptive data. Additionally, the research introduces a dynamic adjustment mechanism to adapt the filter parameters in real-time, based on evolving attack patterns and system conditions. Extensive simulations demonstrate the effectiveness of the proposed framework in maintaining high levels of detection accuracy and system reliability despite the presence of deceptive attacks. The findings underscore the critical need for innovative and adaptive strategies to address the challenges posed by sophisticated cyber threats in unmanned marine systems, providing valuable insights and practical solutions for enhancing the operational integrity and security of UMVs.
Submission Number: 249
Loading