arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1906.00335cs.CV
收藏

边缘检测的对抗性例子:它们存在,它们转移

Adversarial Examples for Edge Detection: They Exist, and They Transfer

The Johns Hopkins University(约翰斯·霍普金斯大学)

Christian Cosgrove, Alan L. Yuille

摘要:

卷积神经网络最近在包括边缘和对象边界检测的许多任务中已经发展了现有技术。然而,在本文中,我们证明了这些边缘检测器继承了神经网络的一个令人不安的特性:它们可以被对抗性的例子所欺骗。我们发现,添加小扰动的图像导致HED,基于CNN的边缘检测模型,无法定位边缘,检测不存在的边缘,甚至幻觉任意配置的边缘。更令人惊讶的是,我们发现这些对抗性的例子转移到其他基于CNN的视觉模型。特别是,对边缘检测的攻击会导致训练用于执行图像分类和语义分割等不相关的高级任务的模型的准确性显著下降。我们的代码将被公开。

英文摘要:

Convolutional neural networks have recently advanced the state of the art in many tasks including edge and object boundary detection. However, in this paper, we demonstrate that these edge detectors inherit a troubling property of neural networks: they can be fooled by adversarial examples. We show that adding small perturbations to an image causes HED, a CNN-based edge detection model, to fail to locate edges, to detect nonexistent edges, and even to hallucinate arbitrary configurations of edges. More surprisingly, we find that these adversarial examples transfer to other CNN-based vision models. In particular, attacks on edge detection result in significant drops in accuracy in models trained to perform unrelated, high-level tasks like image classification and semantic segmentation. Our code will be made public.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑