ShadowNet: A Secure and Efficient System for On-device Model Inference

With the increased usage of AI accelerators on mobile and edge devices, on-device machine learning (ML) is gaining popularity. Consequently, thousands of proprietary ML models are being deployed on billions of untrusted devices. This raises serious security concerns about model privacy. However, protecting the model privacy without losing access to the AI accelerators is a challenging problem. In this paper, we present a novel on-device model inference system, ShadowNet. ShadowNet protects the model privacy with Trusted Execution Environment (TEE) while securely outsourcing the heavy linear layers of the model to the untrusted hardware accelerators. ShadowNet achieves this by transforming the weights of the linear layers before outsourcing them and restoring the results inside the TEE. The nonlinear layers are also kept secure inside the TEE. The transformation of the weights and the restoration of the results are designed in a way that can be implemented efficiently. We have built a ShadowNet prototype based on TensorFlow Lite and applied it on four popular CNNs, namely, MobileNets, ResNet-44, AlexNet and MiniVGG. Our evaluation shows that ShadowNet achieves strong security guarantees with reasonable performance, offering a practical solution for secure on-device model inference.