Towards Building Secure UAV Navigation with FHE-aware Knowledge Distillation

TL;DR

This paper introduces a novel framework combining Reinforcement Learning, Fully Homomorphic Encryption, and Knowledge Distillation to enable secure, real-time UAV navigation with significantly reduced latency and maintained high accuracy.

Contribution

It presents a new approach that uses Knowledge Distillation to compress encrypted neural networks, making secure UAV navigation feasible with FHE while preserving performance.

Findings

18x speedup in network inference time

High correlation with original model (R-squared 0.9499)

Demonstrates practical secure UAV navigation with encrypted data

Abstract

In safeguarding mission-critical systems, such as Unmanned Aerial Vehicles (UAVs), preserving the privacy of path trajectories during navigation is paramount. While the combination of Reinforcement Learning (RL) and Fully Homomorphic Encryption (FHE) holds promise, the computational overhead of FHE presents a significant challenge. This paper proposes an innovative approach that leverages Knowledge Distillation to enhance the practicality of secure UAV navigation. By integrating RL and FHE, our framework addresses vulnerabilities to adversarial attacks while enabling real-time processing of encrypted UAV camera feeds, ensuring data security. To mitigate FHE's latency, Knowledge Distillation is employed to compress the network, resulting in an impressive 18x speedup without compromising performance, as evidenced by an R-squared score of 0.9499 compared to the original model's score of 0.9631. Our methodology underscores the feasibility of processing encrypted data for UAV navigation tasks, emphasizing security alongside performance efficiency and timely processing. These findings pave the way for deploying autonomous UAVs in sensitive environments, bolstering their resilience against potential security threats.