TBNet: A Neural Architectural Defense Framework Facilitating DNN Model Protection in Trusted Execution Environments
This work addresses security and performance issues for DNN model protection on edge devices, representing an incremental improvement over existing TEE solutions.
The paper tackles the problem of securing DNN models on edge devices using Trusted Execution Environments (TEEs) by proposing TBNet, a defense framework that reduces latency and protects models, achieving efficient protection at low cost as demonstrated on a Raspberry Pi.
Trusted Execution Environments (TEEs) have become a promising solution to secure DNN models on edge devices. However, the existing solutions either provide inadequate protection or introduce large performance overhead. Taking both security and performance into consideration, this paper presents TBNet, a TEE-based defense framework that protects DNN model from a neural architectural perspective. Specifically, TBNet generates a novel Two-Branch substitution model, to respectively exploit (1) the computational resources in the untrusted Rich Execution Environment (REE) for latency reduction and (2) the physically-isolated TEE for model protection. Experimental results on a Raspberry Pi across diverse DNN model architectures and datasets demonstrate that TBNet achieves efficient model protection at a low cost.