Saved in:
Bibliographic Details
Main Authors: An, Qiyuan, Sevastopoulos, Christos, Makedon, Fillia
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2402.08763
Tags: Add Tag
No Tags, Be the first to tag this record!
Table of Contents:
  • 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.