J Wang, R Bao, Z Zhang, H Zhao - IEEE/ACM Transactions on …, 2022 - ieeexplore.ieee.org
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 …
Z Wang, Z Liu, X Zheng, Q Su… - Proceedings of the 61st …, 2023 - aclanthology.org
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 …