SyncGait: Robust Long-Distance Authentication for Drone Delivery via Implicit Gait Behaviors

By: Zijian Ling, Man Zhou, Hongda Zhai, Yating Huang, Lingchen Zhao, Qi Li, Chao Shen, Qian Wang

Published: 2025-12-29

View on arXiv →
#cs.AI

Abstract

SyncGait is a novel user-drone mutual authentication system that leverages implicit gait behaviors, specifically the user's unique arm swing, for robust long-distance authentication during drone delivery. It requires no additional hardware or explicit user actions, operating seamlessly using smartphone IMU sensors and drone cameras. Extensive experiments demonstrate 99.84% accuracy at over 18m distance and strong resilience against spoofing attacks, offering a secure and user-friendly solution for real-world drone logistics.

FEEDBACK

Projects

No projects yet

SyncGait: Robust Long-Distance Authentication for Drone Delivery via Implicit Gait Behaviors | ArXiv Intelligence