Adversarial Attack On Yolov5 For Traffic And Road Sign Detection

TL;DR

This study evaluates the vulnerability of YOLOv5 object detection to various adversarial attacks in traffic sign detection, revealing significant susceptibility and emphasizing the need for more robust models for safety-critical applications.

Contribution

It systematically investigates multiple adversarial attack methods on YOLOv5 for traffic sign detection, highlighting its vulnerabilities and the importance of developing more secure detection models.

Findings

YOLOv5 is vulnerable to several adversarial attacks.

Misclassification rates increase with attack strength.

Saliency maps help explain attack impacts.

Abstract

This paper implements and investigates popular adversarial attacks on the YOLOv5 Object Detection algorithm. The paper explores the vulnerability of the YOLOv5 to adversarial attacks in the context of traffic and road sign detection. The paper investigates the impact of different types of attacks, including the Limited memory Broyden Fletcher Goldfarb Shanno (L-BFGS), the Fast Gradient Sign Method (FGSM) attack, the Carlini and Wagner (C&W) attack, the Basic Iterative Method (BIM) attack, the Projected Gradient Descent (PGD) attack, One Pixel Attack, and the Universal Adversarial Perturbations attack on the accuracy of YOLOv5 in detecting traffic and road signs. The results show that YOLOv5 is susceptible to these attacks, with misclassification rates increasing as the magnitude of the perturbations increases. We also explain the results using saliency maps. The findings of this paper have important implications for the safety and reliability of object detection algorithms used in traffic and transportation systems, highlighting the need for more robust and secure models to ensure their effectiveness in real-world applications.