← Search

Rongzhou Bao

2 accepted papers

2022

Distinguishing Non-natural from Natural Adversarial Samples for More Robust Pre-trained Language Model

ACL 2022findings

Recently, the problem of robustness of pre-trained language models (PrLMs) has received increasing research interest. Latest studies on adversarial attacks achieve high attack success rates against PrLMs, claiming that PrLMs are not robust. However, we find that the adversarial samples that PrLMs fa…