arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2006.09701cs.CVcs.LG
收藏

潜在风格转换的对抗性防御

Adversarial Defense by Latent Style Transformations

CSIRO’s Data61(澳大利亚联邦科学与工业研究组织Data61);Monash University(莫纳什大学)

Shuo Wang, Surya Nepal, Alsharif Abuadbba, Carsten Rudolph, Marthie Grobler

摘要:

机器学习模型已经证明了对对抗攻击的脆弱性,更具体地说,是对对抗示例的错误分类。在本文中,我们研究了一个攻击不可知防御对抗攻击的高分辨率图像检测可疑输入。我们的方法背后的直觉是,正常图像的基本特征通常与非基本样式转换一致,例如,稍微改变人像的面部表情。相反,对抗性示例通常对这种转换敏感。在我们的方法来检测敌对的情况下,我们提出了一个在\underline{V} ertible \underline{A} utoencoder的基础上的\underline{S} tyleGAN2生成器通过\underline{A}对抗训练(VASA),以逆图像解开潜在代码,揭示层次风格。然后,我们建立了一组编辑的副本与非必要的风格转换,通过执行潜在的移位和重建,基于潜代码和风格转换之间的对应关系。这些编辑副本的基于分类的一致性用于区分对抗实例。

英文摘要:

Machine learning models have demonstrated vulnerability to adversarial attacks, more specifically misclassification of adversarial examples. In this paper, we investigate an attack-agnostic defense against adversarial attacks on high-resolution images by detecting suspicious inputs. The intuition behind our approach is that the essential characteristics of a normal image are generally consistent with non-essential style transformations, e.g., slightly changing the facial expression of human portraits. In contrast, adversarial examples are generally sensitive to such transformations. In our approach to detect adversarial instances, we propose an in\underline{V}ertible \underline{A}utoencoder based on the \underline{S}tyleGAN2 generator via \underline{A}dversarial training (VASA) to inverse images to disentangled latent codes that reveal hierarchical styles. We then build a set of edited copies with non-essential style transformations by performing latent shifting and reconstruction, based on the correspondences between latent codes and style transformations. The classification-based consistency of these edited copies is used to distinguish adversarial instances.

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。

↑