2025
LoRO: Real-Time on-Device Secure Inference for LLMs via TEE-Based Low Rank Obfuscation
NeurIPS 2025poster
While Large Language Models (LLMs) have gained remarkable success, they are consistently at risk of being stolen when deployed on untrusted edge devices. As a solution, TEE-based secure inference has been proposed to protect valuable model property. However, we identify a statistical vulnerability i…