An ML-driven PLA Scheme for Inter-Satellite Communication

Satellite communication is expected to play a key role in future networks due to its ability to deliver wide-area coverage and high-capacity links. Inter-satellite communication (ISC), which facilitates real-time data exchange between satellites, is therefore critical for important satellite applications such as navigation, earth observation, and defense. However, the broadcast nature of the wireless medium renders ISC vulnerable to various security threats. In this paper, we investigate impersonation attack scenarios in LEO ISC and propose a novel machine learning (ML)-based physical layer authentication (PLA) scheme. The proposed method leverages Doppler frequency shift (DFS) features, arising from relative satellite motion, to enable secure authentication of the transmitting satellite. To address the challenge of acquiring ground-truth labels, we employ a long short-term memory (LSTM) network to learn temporal patterns from the satellite dynamics. A synthetic dataset simulating a 30-day mission involving three satellites (two legitimate and one malicious) is generated using a MATLAB-based orbital propagation method, incorporating 3D position and velocity vectors. The LSTM model is trained on 25 days of data from legitimate satellites and evaluated over the remaining 5 days using both legitimate and malicious transmissions. Authentication is performed via binary hypothesis testing, and we derive tractable analytical expressions for the false alarm and missed detection probabilities and validate the results through simulations.