paperSeptember 2026Unreviewed

Understanding the Security Boundary of Obfuscation-based On-Device LLM Protection

Hanyi Zhou, Chenyang Li, Yuanzhe Pang, Ke Xu, Mingwei Xu, Zhuotao Liu

Abstract

Trusted Execution Environments (TEEs) offer a promising mechanism for safeguarding the intellectual property of on-device Large Language Models (LLMs). To overcome the inherent computational bottlenecks of TEEs, existing TEE-Shielded LLM Partition (TSLP) methods apply efficient obfuscation schemes to computationally intensive layers, offloading them to external GPUs while retaining only lightweight operations within the TEE. Although a growing body of TSLP-based approaches has emerged, these def

Cite

@misc{zhou2026understanding,
  title = {{Understanding the Security Boundary of Obfuscation-based On-Device LLM Protection}},
  author = {Hanyi Zhou and Chenyang Li and Yuanzhe Pang and Ke Xu and Mingwei Xu and Zhuotao Liu},
  year = {2026},
  month = sep,
  eprint = {2609.10117},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2609.10117}
}