In the past few years, it has become increasingly evident that deep neural networks are not
resilient enough to withstand adversarial perturbations in input data, leaving them …

Recent advances in instruction-following large language models (LLMs) have led to
dramatic improvements in a range of NLP tasks. Unfortunately, we find that the same …

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

Recently, the adversarial attack and defense technology has made remarkable
achievements and has been widely applied in the computer vision field, promoting its rapid …

High-performance neural language models have obtained state-of-the-art results on a wide
range of Natural Language Processing (NLP) tasks. However, results for common …

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

Deep neural networks (DNNs) have achieved remarkable success in various tasks (eg,
image classification, speech recognition, and natural language processing (NLP)). However …

Deep neural networks (DNNs) have been widely used in many fields due to their powerful
representation learning capabilities. However, they are exposed to serious threats caused …

Textual adversarial samples play important roles in multiple subfields of NLP research,
including security, evaluation, explainability, and data augmentation. However, most work …

Word-level adversarial attacks have shown success in NLP models, drastically decreasing
the performance of transformer-based models in recent years. As a countermeasure …