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

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