3 papers
cs.LG2026
OSNIP: Breaking the Privacy-Utility-Efficiency Trilemma in LLM Inference via Obfuscated Semantic Null Space
Zhiyuan Cao, Zeyu Ma, Chenhao Yang +2
We propose Obfuscated Semantic Null space Injection for Privacy (OSNIP), a lightweight client-side encryption framework for privacy-preserving LLM inference. Generalizing the geome…
cs.AI2025
TestAgent: Automatic Benchmarking and Exploratory Interaction for Evaluating LLMs in Vertical Domains
Wanying Wang, Zeyu Ma, Xuhong Wang +3
As Large Language Models (LLMs) are increasingly deployed in highly specialized vertical domains, the evaluation of their domain-specific performance becomes critical. However, exi…
cs.AI2025
Self-Aware Safety Augmentation: Leveraging Internal Semantic Understanding to Enhance Safety in Vision-Language Models
Wanying Wang, Zeyu Ma, Han Zheng +2
Large vision-language models (LVLMs) are vulnerable to harmful input compared to their language-only backbones. We investigated this vulnerability by exploring LVLMs internal dynam…