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!
_version_ 1866910329411207168
author An, Qiyuan
Sevastopoulos, Christos
Makedon, Fillia
author_facet An, Qiyuan
Sevastopoulos, Christos
Makedon, Fillia
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.
format Preprint
id arxiv_https___arxiv_org_abs_2402_08763
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Enhancing Robustness of Indoor Robotic Navigation with Free-Space Segmentation Models Against Adversarial Attacks
An, Qiyuan
Sevastopoulos, Christos
Makedon, Fillia
Computer Vision and Pattern Recognition
93C85
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.
title Enhancing Robustness of Indoor Robotic Navigation with Free-Space Segmentation Models Against Adversarial Attacks
topic Computer Vision and Pattern Recognition
93C85
url https://arxiv.org/abs/2402.08763