Abstract :

Satellite Communication Systems Play A Critical Role In Enabling Global Connectivity Across Applications Such As Telecommunications, Navigation, Weather Monitoring, And Defense; However, Their Open And Broadcast Nature Makes Them Highly Vulnerable To Security Threats Including Spoofing, Interference, And Unauthorized Access. Traditional Authentication Techniques Primarily Rely On Cryptographic Mechanisms Such As Encryption And Digital Signatures, Which, Although Effective, Suffer From Limitations Like High Computational Overhead, Key Management Complexity, And Inefficiency In Resource-constrained Satellite Environments. To Address These Challenges, This Work Proposes A Smart Machine Learning-based Physical Layer Authentication Framework That Leverages Intrinsic Signal Characteristics For Secure Communication. Specifically, The System Utilizes Doppler Shift (DS) And Received Power (RP) As Unique Physical-layer Features To Identify Legitimate Transmitters. A One-Class Support Vector Machine (OCC-SVM) Model Is Employed To Learn Normal Transmission Patterns And Detect Anomalies Corresponding To Malicious Or Spoofed Signals. The Proposed Approach Operates Directly At The Physical Layer, Enabling Low-latency, Adaptive, And Resourceefficient Authentication Without Heavy Reliance On Cryptographic Infrastructure. Experimental Evaluation Demonstrates Improved Detection Accuracy, Reduced False Alarms, And Enhanced Robustness Against Advanced Attacks, Making The System Suitable For Next-generation Satellite Networks And Space-air-ground Integrated Communication Systems.

Published:

07-4-2026

Issue:

Vol. 26 No. 4 (2026)

Page Nos:

1647-1652

Section:

Articles

License:

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

How to Cite