DPAttack: Diffused Patch Attacks against Universal Object Detection
This addresses security risks in object detection systems, but it is incremental as it builds on existing patch attack methods.
The paper tackles the vulnerability of object detectors to adversarial attacks by proposing DPAttack, a diffused patch attack that uses asteroid-shaped or grid-shaped patches to fool detectors while changing only a small number of pixels. It achieved second place in the Alibaba Tianchi competition, demonstrating effectiveness against most object detectors.
Recently, deep neural networks (DNNs) have been widely and successfully used in Object Detection, e.g. Faster RCNN, YOLO, CenterNet. However, recent studies have shown that DNNs are vulnerable to adversarial attacks. Adversarial attacks against object detection can be divided into two categories, whole-pixel attacks and patch attacks. While these attacks add perturbations to a large number of pixels in images, we proposed a diffused patch attack (\textbf{DPAttack}) to successfully fool object detectors by diffused patches of asteroid-shaped or grid-shape, which only change a small number of pixels. Experiments show that our DPAttack can successfully fool most object detectors with diffused patches and we get the second place in the Alibaba Tianchi competition: Alibaba-Tsinghua Adversarial Challenge on Object Detection. Our code can be obtained from https://github.com/Wu-Shudeng/DPAttack.