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

TL;DR

SyncGait addresses the security gap in drone delivery by enabling long-distance, implicit mutual authentication between a user and a drone through hand-held smartphone IMU data and drone video of gait. The approach fuses cross-modal temporal-spatial information using a pipeline that includes adaptive filtering (ADCT), multi-joint Kalman correction (MJCKF), Gradient-Aided AHRS quaternion fusion, and a ResNet+LSTM feature extractor with transfer learning, followed by OC-SVM-based verification. It achieves about $99.84\%$ accuracy at $>18\,m$ with an overall EER near $0.09\%$, and demonstrates strong resistance to radio relay, device hijacking, and mimicry attacks, outperforming prior long-range authentication schemes. The system maintains high performance across devices, environments, and network conditions, suggesting practical deployment potential for secure and user-friendly drone logistics. These results indicate SyncGait as a scalable, hardware-free solution for secure long-distance user–drone authentication in real-world delivery scenarios.

Abstract

In recent years, drone delivery, which utilizes unmanned aerial vehicles (UAVs) for package delivery and pickup, has gradually emerged as a crucial method in logistics. Since delivery drones are expensive and may carry valuable packages, they must maintain a safe distance from individuals until user-drone mutual authentication is confirmed. Despite numerous authentication schemes being developed, existing solutions are limited in authentication distance and lack resilience against sophisticated attacks. To this end, we introduce SyncGait, an implicit gait-based mutual authentication system for drone delivery. SyncGait leverages the user's unique arm swing as he walks toward the drone to achieve mutual authentication without requiring additional hardware or specific authentication actions. We conducted extensive experiments on 14 datasets collected from 31 subjects. The results demonstrate that SyncGait achieves an average accuracy of 99.84\% at a long distance ($>18m$) and exhibits strong resilience against various spoofing attacks, making it a robust, secure, and user-friendly solution in real-world scenarios.

Figures (20)

• Figure 1: The authentication process of SyncGait.
• Figure 2: Different types of attacks.
• Figure 3: The workflow of SyncGait.
• Figure 4: The samples of posture calibration.
• Figure 5: The rotational movement in the coordinate system.