ShadowNet: A Secure and Efficient On-device Model Inference System for Convolutional Neural Networks. (arXiv:2011.05905v3 [cs.CR] UPDATED)

With the increased usage of AI accelerators on mobile and edge devices,
on-device machine learning (ML) is gaining popularity. Thousands of proprietary
ML models are being deployed today on billions of untrusted devices. This
raises serious security concerns about model privacy. However, protecting model
privacy without losing access to the untrusted 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 …

device networks neural networks system