Secure Deep Learning-based Distributed Intelligence on Pocket-sized Drones

TL;DR

This paper introduces a secure distributed deep learning scheme for nano-drones that offloads computation to fog nodes, ensuring security and improved accuracy in visual pose estimation despite resource constraints.

Contribution

It proposes a novel distributed execution scheme that validates fog computations through redundant subnetwork execution, enhancing security and accuracy.

Findings

Improves $R^2$ score by +0.19 over onboard-only models.

Detects attacks within 2 seconds with 95% probability.

Enables secure deep learning on resource-limited nano-drones.

Abstract

Palm-sized nano-drones are an appealing class of edge nodes, but their limited computational resources prevent running large deep-learning models onboard. Adopting an edge-fog computational paradigm, we can offload part of the computation to the fog; however, this poses security concerns if the fog node, or the communication link, can not be trusted. To tackle this concern, we propose a novel distributed edge-fog execution scheme that validates fog computation by redundantly executing a random subnetwork aboard our nano-drone. Compared to a State-of-the-Art visual pose estimation network that entirely runs onboard, a larger network executed in a distributed way improves the $R^2$ score by +0.19; in case of attack, our approach detects it within 2s with 95% probability.