Pre-trained contextualized language models (PrLMs) have led to strong performance gains
in downstream natural language understanding tasks. However, PrLMs can still be easily …

Although pre-trained language models (PrLMs) have achieved significant success, recent
studies demonstrate that PrLMs are vulnerable to adversarial attacks. By generating …

Large-scale pre-trained language models have achieved tremendous success across a
wide range of natural language understanding (NLU) tasks, even surpassing human …

Despite neural networks have achieved prominent performance on many natural language
processing (NLP) tasks, they are vulnerable to adversarial examples. In this paper, we …

Pretrained language models (PLMs) perform poorly under adversarial attacks. To improve
the adversarial robustness, adversarial data augmentation (ADA) has been widely adopted …

Adversarial attacks on deep neural networks keep raising security concerns in natural
language processing research. Existing defenses focus on improving the robustness of the …

Abstract Language models are known to be vulnerable to textual adversarial attacks, which
add humanimperceptible perturbations to the input to mislead DNNs. It is thus imperative to …

Generating high-quality textual adversarial examples is critical for investigating the pitfalls of
natural language processing (NLP) models and further promoting their robustness. Existing …

Recent studies have shown that deep neural networks are vulnerable to intentionally crafted
adversarial examples, and various methods have been proposed to defend against …

Although deep neural networks have achieved prominent performance on many NLP tasks,
they are vulnerable to adversarial examples. We propose Dirichlet Neighborhood Ensemble …