3 papers
cs.CR2026
CoreGuard: Safeguarding Foundational Capabilities of LLMs Against Model Stealing in Edge Deployment
Qinfeng Li, Tianyue Luo, Xuhong Zhang +8
Proprietary large language models (LLMs) exhibit strong generalization capabilities across diverse tasks and are increasingly deployed on edge devices for efficiency and privacy re…
cs.DC2026
ACE-Bench: A Lightweight Benchmark for Evaluating Azure SDK Usage Correctness
Wenxing Zhu, Simeng Qi, Junkui Chen +7
We present ACE-Bench (Azure SDK Coding Evaluation Benchmark), an execution-free benchmark that provides fast, reproducible pass or fail signals for whether large language model (LL…
cs.CR2024
TransLinkGuard: Safeguarding Transformer Models Against Model Stealing in Edge Deployment
Qinfeng Li, Zhiqiang Shen, Zhenghan Qin +4
Proprietary large language models (LLMs) have been widely applied in various scenarios. Additionally, deploying LLMs on edge devices is trending for efficiency and privacy reasons.…