02/02/2021

EvaLDA: Efficient Evasion Attacks Towards Latent Dirichlet Allocation

Qi Zhou, Haipeng Chen, Yitao Zheng, Zhen Wang

Keywords:

Abstract Paper Similar Papers

Abstract: As one of the most powerful topic models, Latent Dirichlet Allocation (LDA) has been used in a vast range of tasks, including document understanding, information retrieval and peer-reviewer assignment. Despite its tremendous popularity, the security of LDA has rarely been studied. This poses severe risks to security-critical tasks such as sentiment analysis and peer-reviewer assignment that are based on LDA. In this paper, we are interested in knowing whether LDA models are vulnerable to adversarial perturbations of benign document examples during inference time. We formalize the evasion attack to LDA models as an optimization problem and prove it to be NP-hard. We then propose a novel and efficient algorithm, EvaLDA to solve it. We show the effectiveness of EvaLDA via extensive empirical evaluations. For instance, in the NIPS dataset, EvaLDA can averagely promote the rank of a target topic from 10 to around 7 by only replacing 1% of the words with similar words in a victim document. Our work provides significant insights into the power and limitations of evasion attacks to LDA models.

The video of this talk cannot be embedded. You can watch it here:
https://slideslive.com/38948262
(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
 17:50 
 0
 0
 0
 0
 7:18 
 0
 0
 0
 0
 5:00 
 0
 0
 0
 0
 3:17 
 0
 0
 0
 0
 3:23 
 0
 0
 0
 0
 10:53 
 0
 0
 0
 0
 3:12 
 0
 0
 0
 0
 5:01 
 0
 0
 0
 0
 5:16 
 0
 0
 0
 0
 1:00 
 0
 0
 0
 0
 18:49 
 0
 0
 0
 0
 10:21 
 0
 0
 0
 0
 3:56 
 0
 0
 0
 0
 2:48 
 0
 0
 0
 0
 11:15 
 0
 0
 0
 0
 14:36 
 0
 0
 0
 0
 5:51 
 0
 0
 0
 0
 5:03 
 0
 0
 0
 0
 14:24 
 0
 0
 0
 0
 13:48 
 0
 0
 0
 0
 1:01 
 0
 0
 0
 0
 2:18 
 1
 0
 0
 1
 3:22 
 0
 0
 0
 1
 5:06 
 0
 0
 0
 0
 4:56 
 0
 0
 0
 0
 15:40 
 0
 0
 0
 0
 14:56 
 0
 0
 0
 0
 17:53 
 0
 0
 0
 0
 12:40 
 0
 0
 0
 0
 3:21 
 0
 0
 0
 0
 3:05 
 0
 0
 0
 0
 16:07 
 0
 0
 0
 0
 16:16 
 0
 0
 0
 0
 14:10 
 0
 0
 0
 0
 7:37 
 0
 0
 0
 0
 14:42 
 0
 0
 0
 0
 6:36 
 0
 0
 0
 0
 3:02 
 0
 0
 0
 0
 12:38 
 0
 0
 0
 0
 14:13