02/02/2021

Towards Feature Space Adversarial Attack by Style Perturbation

Qiuling Xu, Guanhong Tao, Siyuan Cheng, Xiangyu Zhang

Keywords:

Abstract Paper Similar Papers

Abstract: We propose a new adversarial attack to Deep Neural Networks for image classification. Different from most existing attacks that directly perturb input pixels, our attack focuses on perturbing abstract features, more specifically, features that denote styles, including interpretable styles such as vivid colors and sharp outlines, and uninterpretable ones. It induces model misclassification by injecting imperceptible style changes through an optimization procedure. We show that our attack can generate adversarial samples that are more natural-looking than the state-of-the-art unbounded attacks. The experiment also supports that existing pixel-space adversarial attack detection and defense techniques can hardly ensure robustness in the style-related feature space.

The video of this talk cannot be embedded. You can watch it here:
https://slideslive.com/38949263
(Link will open in new window)
 0
 0
 0
 0
  Share    
This is an embedded video. Talk and the respective paper are published at AAAI 2021 virtual conference. If you are one of the authors of the paper and want to manage your upload, see the question "My papertalk has been externally embedded..." in the FAQ section.

Comments

Post Comment
no comments yet
code of conduct: tbd Characters remaining: 140

Similar Papers

 0
 0
 0
 0
 12:46 
 0
 0
 0
 0
 1:01 
 0
 0
 0
 0
 3:04 
 0
 0
 0
 0
 1:01 
 0
 0
 0
 0
 18:19 
 0
 0
 0
 0
 4:56 
 0
 0
 0
 0
 3:23 
 0
 0
 0
 0
 1:01 
 0
 0
 0
 0
 3:59 
 0
 0
 0
 0
 17:17 
 0
 0
 0
 0
 3:51 
 0
 0
 0
 0
 14:46 
 0
 0
 0
 0
 1:03 
 0
 0
 0
 0
 2:57 
 0
 0
 0
 0
 5:28 
 0
 0
 0
 0
 5:00 
 0
 0
 0
 0
 1:01 
 0
 0
 0
 0
 17:14 
 0
 0
 0
 0
 1:01 
 0
 0
 0
 0
 4:56 
 0
 0
 0
 0
 4:57 
 0
 0
 0
 0
 14:14 
 0
 0
 0
 0
 4:34 
 0
 0
 0
 0
 1:01 
 0
 0
 0
 0
 9:34 
 0
 0
 0
 0
 1:01 
 0
 0
 0
 0
 12:37 
 0
 0
 0
 0
 3:19 
 0
 0
 0
 0
 15:48 
 0
 0
 0
 0
 1:01 
 0
 0
 0
 0
 5:02 
 0
 0
 0
 0
 11:21 
 0
 0
 0
 0
 3:29 
 0
 0
 0
 0
 2:58 
 0
 0
 0
 0
 5:19 
 0
 0
 0
 0
 11:59 
 0
 0
 0
 0
 15:17 
 0
 0
 0
 0
 8:43 
 0
 0
 0
 0
 1:01 
 0
 0
 0
 0
 5:03