CRDec 10, 2021

Towards Homomorphic Inference Beyond the Edge

arXiv:2112.08943v1
Originality Incremental advance
AI Analysis

This addresses energy constraints for beyond-edge devices operating in remote areas, though it appears incremental as it builds on existing homomorphic encryption and in-memory computation techniques.

The paper tackles the problem of high energy costs for long-distance communication in beyond-edge devices by developing a device that acts as a nearby server for offloading computation on encrypted data, achieving a speedup within a power budget of a few milliWatts.

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.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes