Existing studies have demonstrated that adversarial examples can be directly attributed to the presence of non-robust features, which are highly predictive, but can be easily manipulated by adversaries to fool NLP models. In this study, we explore the feasibility of capturing task-specific robust features, while eliminating the non-robust ones by using the information bottleneck theory. Through extensive experiments, we show that the models trained with our information bottleneck-based method are able to achieve a significant improvement in robust accuracy, exceeding performances of all the previously reported defense methods while suffering almost no performance drop in clean accuracy on SST-2, AGNEWS and IMDB datasets.
@article{arxiv.2206.05511,
title = {Improving the Adversarial Robustness of NLP Models by Information Bottleneck},
author = {Cenyuan Zhang and Xiang Zhou and Yixin Wan and Xiaoqing Zheng and Kai-Wei Chang and Cho-Jui Hsieh},
journal= {arXiv preprint arXiv:2206.05511},
year = {2022}
}