Yier Jin — accepted AI-conference papers

2026

PragLocker: Protecting Agent Intellectual Property in Untrusted Deployments via Non-Portable Prompts

Qinfeng Li, Yuntai Bao, Jianghui Hu, Wenqi Zhang, Jintao Chen, Huifeng Zhu +2

ICML 2026poster

LLM agents rely on prompts to implement task-specific capabilities based on foundation LLMs, making agent prompts valuable intellectual property. However, in untrusted deployments, adversaries can copy and reuse these prompts with other proprietary LLMs, causing economic losses. To protect these pro…

Cited by 0 Source ↗Scholar ↗

2025

CoreGuard: Safeguarding Foundational Capabilities of LLMs Against Model Stealing in Edge Deployment

Qinfeng Li, Tianyue Luo, Xuhong Zhang, Yangfan Xie, Zhiqiang Shen, Lijun Zhang +5

NeurIPS 2025poster

Proprietary large language models (LLMs) exhibit strong generalization capabilities across diverse tasks and are increasingly deployed on edge devices for efficiency and privacy reasons. However, deploying proprietary LLMs at the edge without adequate protection introduces critical security threats.…

Cited by 0 Source ↗Scholar ↗