3 papers
cs.CL2026
SEP-Attack: A Simple and Effective Paradigm for Transfer-Based Textual Adversarial Attack
Han Liu, Zhi Xu, Xiaotong Zhang +5
Despite the strong performance of deep neural networks in modern Web and language applications, they remain vulnerable to adversarial attacks, especially transferable attacks that…
cs.CL2026
Defragmenting Language Models: An Interpretability-based Approach for Vocabulary Expansion
Maitrey Mehta, Nishant Subramani, Zhichao Xu +2
All languages are equal; when it comes to tokenization, some are more equal than others. Tokens are the hidden currency that dictate the cost and latency of access to contemporary…
cs.CV2026
HQA-VLAttack: Towards High Quality Adversarial Attack on Vision-Language Pre-Trained Models
Han Liu, Jiaqi Li, Zhi Xu +5
Black-box adversarial attack on vision-language pre-trained models is a practical and challenging task, as text and image perturbations need to be considered simultaneously, and on…