Federated Graph Learning for Low Probability of Detection in Wireless Ad-Hoc Networks
This addresses the problem of enhancing privacy and security in wireless networks for users by concealing communication existence, though it appears incremental as it builds on existing LPD concepts with a new method.
The paper tackles the problem of minimizing the detectability of wireless ad-hoc networks by developing a privacy-preserving, distributed framework using graph neural networks to predict optimal communication regions for nodes, achieving results measured by mean absolute error and median absolute error.
Low probability of detection (LPD) has recently emerged as a means to enhance the privacy and security of wireless networks. Unlike existing wireless security techniques, LPD measures aim to conceal the entire existence of wireless communication instead of safeguarding the information transmitted from users. Motivated by LPD communication, in this paper, we study a privacy-preserving and distributed framework based on graph neural networks to minimise the detectability of a wireless ad-hoc network as a whole and predict an optimal communication region for each node in the wireless network, allowing them to communicate while remaining undetected from external actors. We also demonstrate the effectiveness of the proposed method in terms of two performance measures, i.e., mean absolute error and median absolute error.