2 papers
cs.CL2025
Crabs: Consuming Resource via Auto-generation for LLM-DoS Attack under Black-box Settings
Yuanhe Zhang, Zhenhong Zhou, Wei Zhang +4
Large Language Models (LLMs) have demonstrated remarkable performance across diverse tasks yet still are vulnerable to external threats, particularly LLM Denial-of-Service (LLM-DoS…
cs.LG2025
An Optimization Algorithm for Multimodal Data Alignment
Wei Zhang, Xinyue Wang, Lan Yu +1
In the data era, the integration of multiple data types, known as multimodality, has become a key area of interest in the research community. This interest is driven by the goal to…