Saved in:
Bibliographic Details
Main Author: Yang, Jinghan
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2411.17026
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912133779816448
author Yang, Jinghan
author_facet Yang, Jinghan
contents The classification of road signs by autonomous systems, especially those reliant on visual inputs, is highly susceptible to adversarial attacks. Traditional approaches to mitigating such vulnerabilities have focused on enhancing the robustness of classification models. In contrast, this paper adopts a fundamentally different strategy aimed at increasing robustness through the redesign of road signs themselves. We propose an attacker-agnostic learning scheme to automatically design road signs that are robust to a wide array of patch-based attacks. Empirical tests conducted in both digital and physical environments demonstrate that our approach significantly reduces vulnerability to patch attacks, outperforming existing techniques.
format Preprint
id arxiv_https___arxiv_org_abs_2411_17026
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle RED: Robust Environmental Design
Yang, Jinghan
Computer Vision and Pattern Recognition
The classification of road signs by autonomous systems, especially those reliant on visual inputs, is highly susceptible to adversarial attacks. Traditional approaches to mitigating such vulnerabilities have focused on enhancing the robustness of classification models. In contrast, this paper adopts a fundamentally different strategy aimed at increasing robustness through the redesign of road signs themselves. We propose an attacker-agnostic learning scheme to automatically design road signs that are robust to a wide array of patch-based attacks. Empirical tests conducted in both digital and physical environments demonstrate that our approach significantly reduces vulnerability to patch attacks, outperforming existing techniques.
title RED: Robust Environmental Design
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2411.17026