Confidential Deep Learning: Executing Proprietary Models on Untrusted Devices
This addresses intellectual property protection for model providers in edge computing scenarios, though it is incremental as it builds on existing hardware security features.
The paper tackles the problem of protecting proprietary deep learning models when run on untrusted end-user devices by proposing the use of ARM TrustZone hardware security, aiming to minimize performance overhead while ensuring confidentiality.
Performing deep learning on end-user devices provides fast offline inference results and can help protect the user's privacy. However, running models on untrusted client devices reveals model information which may be proprietary, i.e., the operating system or other applications on end-user devices may be manipulated to copy and redistribute this information, infringing on the model provider's intellectual property. We propose the use of ARM TrustZone, a hardware-based security feature present in most phones, to confidentially run a proprietary model on an untrusted end-user device. We explore the limitations and design challenges of using TrustZone and examine potential approaches for confidential deep learning within this environment. Of particular interest is providing robust protection of proprietary model information while minimizing total performance overhead.