An Experimental Study of Trojan Vulnerabilities in UAV Autonomous Landing

TL;DR

This paper explores Trojan vulnerabilities in UAV autonomous landing systems, demonstrating how embedded triggers can cause significant failures in deep learning models used for navigation.

Contribution

It provides an experimental assessment of Trojan attack impacts on UAV landing systems and introduces an evaluation framework for detecting infected models.

Findings

Accuracy drops from 96.4% to 73.3% under Trojan triggers

Developed a dataset simulating real-world conditions

Created an evaluation framework for Trojan detection

Abstract

This study investigates the vulnerabilities of autonomous navigation and landing systems in Urban Air Mobility (UAM) vehicles. Specifically, it focuses on Trojan attacks that target deep learning models, such as Convolutional Neural Networks (CNNs). Trojan attacks work by embedding covert triggers within a model's training data. These triggers cause specific failures under certain conditions, while the model continues to perform normally in other situations. We assessed the vulnerability of Urban Autonomous Aerial Vehicles (UAAVs) using the DroNet framework. Our experiments showed a significant drop in accuracy, from 96.4% on clean data to 73.3% on data triggered by Trojan attacks. To conduct this study, we collected a custom dataset and trained models to simulate real-world conditions. We also developed an evaluation framework designed to identify Trojan-infected models. This work demonstrates the potential security risks posed by Trojan attacks and lays the groundwork for future research on enhancing the resilience of UAM systems.