arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 2209.09883cs.CV
收藏

利用多目标场景中的局部块差异进行生成式对抗攻击

Leveraging Local Patch Differences in Multi-Object Scenes for Generative Adversarial Attacks

University of California, Riverside(加州大学河滨分校)

Abhishek Aich, Shasha Li, Chengyu Song, M. Salman Asif, Srikanth V. Krishnamurthy, Amit K. Roy-Chowdhury

摘要:

针对图像分类器的最先进的基于生成模型的攻击绝大多数集中在单对象(即,单个主要对象)图像。与这样的设置不同,我们解决了使用多对象(即,多个主要对象)图像,因为它们代表大多数真实世界场景。我们的目标是设计一种攻击策略,该策略可以通过利用此类图像中固有的局部补丁差异(例如,交通场景中对象“人”和对象“自行车”上的局部补丁之间的差异)来从此类自然场景中学习。我们的关键思想是通过混淆图像中每个局部补丁的受害者分类器来错误分类对抗性多对象图像。在此基础上,我们提出了一种新的生成式攻击(称为局部补丁差异或LPD攻击),其中一种新的对比损失函数使用上述多目标场景的特征空间中的局部差异来优化扰动发生器。通过对不同受害者卷积神经网络的各种实验,我们表明,当在不同的白盒和黑盒设置下进行评估时,我们的方法优于具有高度可转移扰动的基线生成攻击。

英文摘要:

State-of-the-art generative model-based attacks against image classifiers overwhelmingly focus on single-object (i.e., single dominant object) images. Different from such settings, we tackle a more practical problem of generating adversarial perturbations using multi-object (i.e., multiple dominant objects) images as they are representative of most real-world scenes. Our goal is to design an attack strategy that can learn from such natural scenes by leveraging the local patch differences that occur inherently in such images (e.g. difference between the local patch on the object `person' and the object `bike' in a traffic scene). Our key idea is to misclassify an adversarial multi-object image by confusing the victim classifier for each local patch in the image. Based on this, we propose a novel generative attack (called Local Patch Difference or LPD-Attack) where a novel contrastive loss function uses the aforesaid local differences in feature space of multi-object scenes to optimize the perturbation generator. Through various experiments across diverse victim convolutional neural networks, we show that our approach outperforms baseline generative attacks with highly transferable perturbations when evaluated under different white-box and black-box settings.

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。

↑