Leveraging Transformer Models for Anti-Jamming in Heavily Attacked UAV Environments

Abstract

In recent years, due to their ability to transmit and relay wireless signals in challenging terrains, Unmanned Aerial Vehicles (UAVs) and High Altitude Platform Stations (HAPS) have become indispensable in various operations in security, emergency, and military campaigns. However, these networks’ ad-hoc structure and open nature make them highly vulnerable to numerous threats and, in particular, to severe jamming attacks. Furthermore, the communication link between a HAPS and multiple UAVs is also under the threat of multiple and different jamming attacks. Addressing these challenges requires innovative and novel methods capable of interactive and proactive defence strategies. To this end, in this study, we propose a method that combines a pseudo-random (PR) algorithm for initial channel selection with a Transformer-based module to predict jammer behavior. This proactive approach significantly enhances the robustness of UAV communications. Our results demonstrate substantial improvements in transmission success rates and prediction accuracy, offering a robust solution for secure UAV and HAPS communications under adverse conditions.

Keywords

• Anti-jamming
• smart jamming
• multiple-jamming
• transformer
• LSTM
• UAVs