Enhancing Robustness of Indoor Robotic Navigation with Free-Space Segmentation Models Against Adversarial Attacks

2024/02/13 by Qiyuan An, An, Qiyuan, Christos Sevastopoulos +3
Computer Science · Physics and Astronomy · #93C85 #Adversarial Robustness in Machine Learning #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Radiation Detection and Scintillator Technologies #Security in Wireless Sensor Networks

paper · pdf · doi:10.48550/arxiv.2402.08763

openalex publication_date 2024/02/13 · openalex created_date 2024/02/16 · openalex updated_date 2026/07/28

Abstract

Endeavors in indoor robotic navigation rely on the accuracy of segmentation models to identify free space in RGB images. However, deep learning models are vulnerable to adversarial attacks, posing a significant challenge to their real-world deployment. In this study, we identify vulnerabilities within the hidden layers of neural networks and introduce a practical approach to reinforce traditional adversarial training. Our method incorporates a novel distance loss function, minimizing the gap between hidden layers in clean and adversarial images. Experiments demonstrate satisfactory performance in improving the model's robustness against adversarial perturbations.

Related

• Enhancing 3D Robotic Vision Robustness by Minimizing Adversarial Mutual Information through a Curriculum Training Approach
• Adversarial Attacks and Detection in Visual Place Recognition for Safer Robot Navigation
• Exploring the Adversarial Vulnerabilities of Vision-Language-Action Models in Robotics
• Is Deep Learning Safe for Robot Vision? Adversarial Examples against the iCub Humanoid
• On the Real-World Adversarial Robustness of Real-Time Semantic Segmentation Models for Autonomous Driving