Deep learning models have achieved great success in many fields, yet they are vulnerable
to adversarial examples. This paper follows a causal perspective to look into the adversarial …

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

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

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

The adversarial attacks against deep neural networks on computer vision tasks have
spawned many new technologies that help protect models from avoiding false predictions …

In the area of natural language processing, deep learning models are recently known to be
vulnerable to various types of adversarial perturbations, but relatively few works are done on …

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

Adversarial attacks are label-preserving modifications to inputs of machine learning
classifiers designed to fool machines but not humans. Natural Language Processing (NLP) …

Adversarial examples expose the vulnerabilities of natural language processing (NLP)
models, and can be used to evaluate and improve their robustness. Existing techniques of …

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