02/02/2021

Deep Feature Space Trojan Attack of Neural Networks by Controlled Detoxification

Siyuan Cheng, Yingqi Liu, Shiqing Ma, Xiangyu Zhang

Keywords:

Abstract Paper Similar Papers

Abstract: Trojan (backdoor) attack is a form of adversarial attack on deep neural networks where the attacker provides victims with a model trained/retrained on malicious data. The backdoor can be activated when a normal input is stamped with a certain pattern called trigger, causing misclassification. Many existing trojan attacks have their triggers being input space patches/objects (e.g., a polygon with solid color) or simple input transformations such as Instagram filters. These simple triggers are susceptible to recent backdoor detection algorithms. We propose a novel deep feature space trojan attack with five characteristics: effectiveness, stealthiness, controllability, robustness and reliance on deep features. We conduct extensive experiments on 9 image classifiers on various datasets including ImageNet to demonstrate these properties and show that our attack can evade state-of-the-art defense.

The video of this talk cannot be embedded. You can watch it here:
https://slideslive.com/38948448
(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
 1:01 
 0
 0
 0
 0
 15:57 
 0
 0
 0
 0
 14:57 
 0
 0
 0
 0
 14:39 
 0
 0
 0
 0
 5:00 
 0
 0
 0
 0
 10:11 
 0
 0
 0
 0
 12:27 
 0
 0
 0
 0
 4:41 
 0
 0
 0
 0
 18:19 
 0
 0
 0
 0
 3:22 
 0
 0
 0
 0
 12:50 
 0
 0
 0
 0
 8:15 
 0
 0
 0
 0
 3:21 
 0
 0
 0
 0
 1:01 
 0
 0
 0
 0
 1:01 
 0
 0
 0
 0
 3:20 
 0
 0
 0
 0
 3:01 
 0
 0
 0
 0
 3:59 
 0
 0
 0
 0
 1:01 
 0
 0
 0
 0
 11:35 
 0
 0
 0
 0
 11:42 
 0
 0
 0
 0
 1:01 
 0
 0
 0
 0
 12:46 
 0
 0
 0
 0
 5:13 
 0
 0
 0
 0
 5:05 
 0
 0
 0
 0
 13:27 
 1
 0
 0
 0
 12:20 
 0
 0
 0
 0
 5:12 
 0
 0
 0
 0
 15:27 
 0
 0
 0
 0
 1:01 
 0
 0
 0
 0
 17:14 
 0
 0
 0
 0
 1:00 
 0
 0
 0
 0
 18:17 
 0
 0
 0
 0
 4:57 
 0
 0
 0
 0
 9:34 
 0
 0
 0
 0
 13:35 
 0
 0
 0
 0
 13:28 
 0
 0
 0
 0
 12:37 
 0
 0
 0
 0
 10:01 
 0
 0
 0
 0
 14:19