论文标题
稀疏的对象攻击对象检测
Sparse Adversarial Attack to Object Detection
论文作者
论文摘要
近年来，对抗性例子引起了很多关注。已经提出了许多对抗性攻击来攻击图像分类器，但很少有工作将注意力转移到对象探测器上。在本文中，我们提出了稀疏的对抗攻击（SAA），使对手能够用有限的\ emph {l $ _ {0} $} norm norm扰动对探测器进行有效的逃避攻击。我们为任务选择图像的脆弱位置，并为任务设计逃避损失函数。 Yolov4和Fasterrcnn的实验结果揭示了我们方法的有效性。此外，我们的SAA在Black-Box攻击设置中显示出跨不同检测器的可传递性。代码可在\ emph {https://github.com/thurssq/tianchi04}中找到。
Adversarial examples have gained tons of attention in recent years. Many adversarial attacks have been proposed to attack image classifiers, but few work shift attention to object detectors. In this paper, we propose Sparse Adversarial Attack (SAA) which enables adversaries to perform effective evasion attack on detectors with bounded \emph{l$_{0}$} norm perturbation. We select the fragile position of the image and designed evasion loss function for the task. Experiment results on YOLOv4 and FasterRCNN reveal the effectiveness of our method. In addition, our SAA shows great transferability across different detectors in the black-box attack setting. Codes are available at \emph{https://github.com/THUrssq/Tianchi04}.
