Defense against Adversarial Attacks in NLP via Dirichlet Neighborhood Ensemble

Cited by: 0|Bibtex|Views52|Links

Abstract:

Despite neural networks have achieved prominent performance on many natural language processing (NLP) tasks, they are vulnerable to adversarial examples. In this paper, we propose Dirichlet Neighborhood Ensemble (DNE), a randomized smoothing method for training a robust model to defense substitution-based attacks. During training, DNE f...More

Code:

Data:

Your rating :
0

 

Tags
Comments