02/02/2021

Generating Natural Language Attacks in a Hard Label Black Box Setting

Rishabh Maheshwary, Saket Maheshwary, Vikram Pudi

Keywords:

Abstract Paper Similar Papers

Abstract: We study an important and challenging task of attacking natural language processing models in a hard label black box setting. We propose a decision-based attack strategy that crafts high quality adversarial examples on text classification and entailment tasks. Our proposed attack strategy leverages population-based optimization algorithm to craft plausible and semantically similar adversarial examples by observing only the top label predicted by the target model. At each iteration, the optimization procedure allow word replacements that maximizes the overall semantic similarity between the original and the adversarial text. Further, our approach does not rely on using substitute models or any kind of training data. We demonstrate the efficacy of our proposed approach through extensive experimentation and ablation studies on five state-of-the-art target models across seven benchmark datasets. In comparison to attacks proposed in prior literature, we are able to achieve a higher success rate with lower word perturbation percentage that too in a highly restricted setting.

The video of this talk cannot be embedded. You can watch it here:
https://slideslive.com/38948632
(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
 14:01 
 0
 0
 0
 0
 13:13 
 0
 0
 0
 0
 3:22 
 0
 0
 0
 0
 5:12 
 0
 0
 0
 0
 16:45 
 0
 0
 0
 0
 12:02 
 0
 0
 0
 0
 1:01 
 0
 0
 0
 0
 11:43 
 0
 0
 0
 0
 9:28 
 0
 0
 0
 0
 4:53 
 0
 0
 0
 0
 9:34 
 0
 0
 0
 0
 17:17 
 0
 0
 0
 0
 1:01 
 0
 0
 0
 0
 9:31 
 0
 0
 0
 0
 17:37 
 0
 0
 0
 0
 19:28 
 0
 0
 0
 0
 16:08 
 0
 0
 0
 0
 5:01 
 0
 0
 0
 0
 16:32 
 0
 0
 0
 0
 11:34 
 0
 0
 0
 0
 3:50 
 0
 0
 0
 0
 10:31 
 0
 0
 0
 0
 4:55 
 0
 0
 0
 0
 6:06 
 0
 0
 0
 0
 12:23 
 0
 0
 0
 0
 12:12 
 0
 0
 0
 0
 15:15 
 0
 0
 0
 0
 15:03 
 0
 0
 0
 0
 14:04 
 0
 0
 0
 0
 15:20 
 0
 0
 0
 0
 15:14 
 0
 0
 0
 0
 4:36 
 0
 0
 0
 0
 17:05 
 0
 0
 0
 0
 15:04 
 0
 0
 0
 0
 16:37 
 0
 0
 0
 0
 1:01 
 0
 0
 0
 0
 11:44 
 0
 0
 0
 0
 5:17 
 0
 0
 0
 0
 11:33 
 0
 0
 0
 0
 9:54