Adversarial Detection: Attacking Object Detection in Real Time

Abstract

Intelligent robots rely on object detection models to perceive the environment. Following advances in deep learning security it has been revealed that object detection models are vulnerable to adversarial attacks. However, prior research primarily focuses on attacking static images or offline videos. Therefore, it is still unclear if such attacks could jeopardize real-world robotic applications in dynamic environments. This paper bridges this gap by presenting the first real-time online attack against object detection models. We devise three attacks that fabricate bounding boxes for nonexistent objects at desired locations. The attacks achieve a success rate of about 90% within about 20 iterations. The demo video is available at https://youtu.be/zJZ1aNlXsMU.

Accepted by IEEE Intelligent Vehicle Symposium, 2023

References in corpus (7)

• YOLOv4: Optimal Speed and Accuracy of Object Detection
• Explaining and Harnessing Adversarial Examples
• Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attacks
• Imperceptible, Robust, and Targeted Adversarial Examples for Automatic Speech Recognition
• On Physical Adversarial Patches for Object Detection
• Adversarial camera stickers: A physical camera-based attack on deep learning systems
• Dynamic Adversarial Patch for Evading Object Detection Models