Privacy-Preserving Inference on the Edge: Mitigating a New Threat Model

Kartik Prabhu, Brian Jun, Pan Hu, Zain Asgar, Sachin Katti, Pete Warden

Keywords: privacy, security, edge inference, embedded, secure enclave, TEE

TL;DR: This paper proposes using a secure enclave for privacy-preserving machine learning at the edge.

Abstract: With the explosion of machine learning at the edge, there's a major need for privacy-preserving machine learning for edge devices. As the number of devices in homes and other private spaces increases, we can expect to see more malicious actors exploiting the inherent recording capabilities in these systems to harm people. This paper proposes that machine learning is not the problem, but rather a solution, which along with the use of a secure enclave, offers a pragmatic approach to preserving privacy. With a simple programming framework, we show how machine learning application developers can be as productive as usual, while still keeping user data private. We demonstrate our implementation for privacy-preserving machine learning on an embedded system, the Nordic NRF5340 PDK with Arm Cotex-M-33, using a relatively large model for person-detection.