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 …

Recently, Large Language Models (LLMs) have made significant advancements and are
now widely used across various domains. Unfortunately, there has been a rising concern …

Natural language processing (NLP) presently has become a new paradigm and enables a
variety of applications such as text classification, information retrieval, and natural language …

Machine learning models trained on human language, also known as Natural Language
Processing (NLP) models, are susceptible to manipulation. These attacks, called NLP …

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

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 …

Hard-label textual adversarial attack is a challenging task, as only the predicted label
information is available, and the text space is discrete and non-differentiable. Relevant …

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

The deployment of large-scale generative models is often restricted by their potential risk of
causing harm to users in unpredictable ways. We focus on the problem of black-box red …

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 …