LoREnc: Low-Rank Encryption for Securing Foundation Models and LoRA Adapters
Researchers have developed LoREnc, a novel framework designed to protect foundation models and their associated low-rank adapters from unauthorized recovery and intellectual property leakage. This training-free method employs spectral truncation and compensation techniques to obscure the foundation model's weights while preserving performance for authorized users. LoREnc achieves this by suppressing dominant low-rank components of the model weights and compensating for the lost information within the adapter, resulting in minimal computational overhead and strong protection against model extraction. AI
IMPACT Introduces a novel method for securing foundation models and adapters against unauthorized recovery, potentially impacting intellectual property protection in generative AI.