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 …

Machine learning (ML) provides effective means to learn from spectrum data and solve
complex tasks involved in wireless communications. Supported by recent advances in …

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

Robustness against word substitutions has a well-defined and widely acceptable form, ie,
using semantically similar words as substitutions, and thus it is considered as a fundamental …

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

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

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 …

We introduce a grey-box adversarial attack and defence framework for sentiment
classification. We address the issues of differentiability, label preservation and input …

Abstract Vision-Language Pre-training (VLP) models have achieved remarkable success in
practice, while easily being misled by adversarial attack. Though harmful, adversarial …

The robustness and security of natural language processing (NLP) models are significantly
important in real-world applications. In the context of text classification tasks, adversarial …