arrow
返回

SSIM-Based Autoencoder Modeling to Defeat Adversarial Patch Attacks

delete2024-10-06
delete1
delete
OA
AI
S
Seungyeol Lee
S
Seongwoo Hong
G
Gwangyeol Kim
J
Jaecheol Ha *
DOI:10.3390/s24196461delete
delete原文链接
delete分享
delete收藏
查看原文
摘要

摘要

En 中文
Object detection systems are used in various fields such as autonomous vehicles and facial recognition. In particular, object detection using deep learning networks enables real-time processing in low-performance edge devices and can maintain high detection rates. However, edge devices that operate far from administrators are vulnerable to various physical attacks by malicious adversaries. In this paper, we implement a function for detecting traffic signs by using You Only Look Once (YOLO) as well as Faster-RCNN, which can be adopted by edge devices of autonomous vehicles. Then, assuming the role of a malicious attacker, we executed adversarial patch attacks with Adv-Patch and Dpatch. Trying to cause misdetection of traffic stop signs by using Adv-Patch and Dpatch, we confirmed the attacks can succeed with a high probability. To defeat these attacks, we propose an image reconstruction method using an autoencoder and the Structural Similarity Index Measure (SSIM). We confirm that the proposed method can sufficiently defend against an attack, attaining a mean Average Precision (mAP) of 91.46% even when two adversarial attacks are launched.
Keyword:
object detection
YOLO
adversarial patch attack
structural similarity index measure
autoencoder
AI总结

AI总结

对已上传原文的论文进行重点信息的提取,主要内容包括:简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。

期刊

Sensors 封面图
Sensors
IF:
3.5
论文数:
7.2W
被引数:
20.9W

机构

H
Hoseo University
学者数:
1.0K
论文数: 1.2K
被引数: 5
引用论文

引用论文

Fixture Optimization in Turning Thin-Wall Components
err2019-10-31
err0
errOAAI
errLisa Croppi; Niccolò Grossi; Antonio Scippa; Gianni Campatelli
err分享
err收藏
err分享
err收藏
Structures and Energies of [Co(CO)n]m (m = 0, 1+, 1−) and HCo(CO)n:  Density Functional Studies
err2002-11-20
err0
PREAI
errChun-Fang Huo; Yong-Wang Li; Gui-Sheng Wu; Matthias Beller; Haijun Jiao
err分享
err收藏
学者 查看更多内容