Recent natural language processing (NLP) techniques have accomplished high
performance on benchmark data sets, primarily due to the significant improvement in the …

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

Adversarial attacks against machine learning models have threatened various real-world
applications such as spam filtering and sentiment analysis. In this paper, we propose a …

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

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 …

Very recently, few certified defense methods have been developed to provably guarantee
the robustness of a text classifier to adversarial synonym substitutions. However, all the …

Dialogue state trackers have made significant progress on benchmark datasets, but their
generalization capability to novel and realistic scenarios beyond the held-out conversations …

We propose the first character-level white-box adversarial attack method against transformer
models. The intuition of our method comes from the observation that words are split into …

Zero/few-shot transfer to unseen services is a critical challenge in task-oriented dialogue
research. The Schema-Guided Dialogue (SGD) dataset introduced a paradigm for enabling …

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