Recent advances in artificial intelligence (AI) have led to its widespread industrial adoption,
with machine learning systems demonstrating superhuman performance in a significant …

Today's world is highly network interconnected owing to the pervasiveness of small personal
devices (eg, smartphones) as well as large computing devices or services (eg, cloud …

Despite efforts to align large language models (LLMs) with human values, widely-used
LLMs such as GPT, Llama, Claude, and PaLM are susceptible to jailbreaking attacks …

Adversarial attacks are carried out to reveal the vulnerability of deep neural networks.
Textual adversarial attacking is challenging because text is discrete and a small perturbation …

As NLP models achieved state-of-the-art performances over benchmarks and gained wide
applications, it has been increasingly important to ensure the safe deployment of these …

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 …

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

Adversarial training is the most empirically successful approach in improving the robustness
of deep neural networks for image classification. For text classification, however, existing …

Existing studies have demonstrated that adversarial examples can be directly attributed to
the presence of non-robust features, which are highly predictive, but can be easily …