Towards Homomorphic Inference Beyond the Edge

TL;DR

This paper introduces a novel beyond edge device that enables encrypted computation with low energy consumption, facilitating secure and efficient inference in remote, power-constrained environments.

Contribution

It presents an energy-efficient in-memory computation method for encrypted inference, reducing communication overhead and enabling secure processing in beyond edge scenarios.

Findings

Achieves encrypted inference within a few milliWatts power budget.

Provides significant speedup for beyond edge applications.

Demonstrates feasibility of secure, low-power remote computation.

Abstract

Beyond edge devices can function off the power grid and without batteries, enabling them to operate in difficult to access regions. However, energy costly long-distance communication required for reporting results or offloading computation becomes a limitation. Here, we reduce this overhead by developing a beyond edge device which can effectively act as a nearby server to offload computation. For security reasons, this device must operate on encrypted data, which incurs a high overhead. We use energy-efficient and intermittent-safe in-memory computation to enable this encrypted computation, allowing it to provide a speedup for beyond edge applications within a power budget of a few milliWatts.