Digital Twin Enabled Simultaneous Learning and Modeling for UAV-assisted Secure Communications with Eavesdropping Attacks

2026-03-23

AI Summary

This work addresses the threat posed by intelligent eavesdropping drones that observe legitimate drone behavior and adaptively adjust their trajectories to maximize information interception, as well as the prohibitive overhead of acquiring global dynamic network states. To tackle these challenges, the authors propose a Digital Twin-driven Simultaneous Learning and Modeling framework (DT-SLAM), which uniquely integrates digital twin technology with reinforcement learning to formulate a multi-stage Stackelberg game. This model jointly optimizes ground user transmissions, UAV trajectories, communication/interference mode switching, and networking topology. A robust Proximal Policy Optimization (RPPO) algorithm is developed to actively explore high-uncertainty regions under model mismatch, significantly enhancing decision-making efficiency and security. Experimental results demonstrate that DT-SLAM improves RPPO convergence speed by approximately 12% and increases secure throughput by 8.6%.

Technology Category

• Search and Optimization: Learning to Search
• Intelligent Robots: State Estimation
• Planning, Routing, and Scheduling: Replanning and Plan Repair

Application Category

• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems
• Security and Privacy: Security and privacy of machine learning and AI applications
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

This paper focuses on secure communications in UAV-assisted wireless networks, which comprise multiple legitimate UAVs (LE-UAVs) and an intelligent eavesdropping UAV (EA-UAV). The intelligent EA-UAV can observe the LE-UAVs'transmission strategies and adaptively adjust its trajectory to maximize information interception. To counter this threat, we propose a mode-switching scheme that enables LE-UAVs to dynamically switch between the data transmission and jamming modes, thereby balancing data collection efficiency and communication security. However, acquiring full global network state information for LE-UAVs' decision-making incurs significant overhead, as the network state is highly dynamic and time-varying. To address this challenge, we propose a digital twin-enabled simultaneous learning and modeling (DT-SLAM) framework that allows LE-UAVs to learn policies efficiently within the DT, thereby avoiding frequent interactions with the real environment. To capture the competitive relationship between the EA-UAV and the LE-UAVs, we model their interactions as a multi-stage Stackelberg game and jointly optimize the GUs' transmission control, UAVs' trajectory planning, mode selection, and network formation to maximize overall secure throughput. Considering potential model mismatch between the DT and the real environment, we propose a robust proximal policy optimization (RPPO) algorithm that encourages LE-UAVs to explore service regions with higher uncertainty. Numerical results demonstrate that the proposed DT-SLAM framework effectively supports the learning process. Meanwhile, the RPPO algorithm converges about 12% faster and the secure throughput can be increased by 8.6% compared to benchmark methods.

Problem

• Secure Communications
• UAV-assisted Networks
• Eavesdropping Attacks
• Digital Twin
• Stackelberg Game

Innovation

• Digital Twin
• Stackelberg Game
• Robust PPO
• Mode-switching
• UAV-assisted Secure Communication