We present a systematic study of the transferability of adversarial attacks on state-of-the-art
object detection frameworks. Using standard detection datasets, we train patterns that …

In this paper, we study physical adversarial attacks on object detectors in the wild. Previous
works mostly craft instance-dependent perturbations only for rigid or planar objects. To this …

Physical adversarial attacks threaten to fool object detection systems, but reproducible
research on the real-world effectiveness of physical patches and how to defend against …

Real-time object detection is one of the key applications of deep neural networks (DNNs) for
real-world mission-critical systems. While DNN-powered object detection systems celebrate …

Deep neural networks (DNNs) are vulnerable to adversarial examples—maliciously crafted
inputs that cause DNNs to make incorrect predictions. Recent work has shown that these …

Physical adversarial attacks against object detectors have seen increasing success in recent
years. However, these attacks require direct access to the object of interest in order to apply …

Object detection is an important vision task and has emerged as an indispensable
component in many vision system, rendering its robustness as an increasingly important …

Most prior works on physical adversarial attacks mainly focus on the attack performance but
seldom enforce any restrictions over the appearance of the generated adversarial patches …

In this paper, we demonstrate a physical adversarial patch attack against object detectors,
notably the YOLOv3 detector. Unlike previous work on physical object detection attacks …

In this paper, we conduct an intriguing experimental study about the physical adversarial
attack on object detectors in the wild. In particular, we learn a camouflage pattern to hide …