In Press                   Back to the articles list | Back to browse issues page

XML Print

An Integrated Threat Model: Quantum Machine Learning Attacks on Satellite Communications and a Multi-Layered Defense Framework
Arash Kosari
Abstract:   (62 Views)
Satellite communications (SATCOM) constitute a fundamental pillar of global connectivity, enabling a diverse range of services that span from civilian telecommunication networks to mission-critical military operations. Despite their strategic importance, these systems face increasingly sophisticated cyber threats particularly at the physical layer that threaten the stability and reliability of operations. In this work, we present the first integrated quantum-enhanced attack model that exploits vulnerabilities in conventional Radio Frequency (RF) based satellite systems by combining Quantum Support Vector Machines (QSVM) with Quantum Random Number Generators (QRNG) . The proposed method utilizes QSVM for high-precision signal prediction and QRNG-driven noise injection for advanced stealth. Simulation results demonstrate an attack success rate of 85% coupled with a low detection probability of 15%. This model is compared with state-of-the-art quantum threats, highlighting its quantum advantages in RF signal processing. Beyond identifying critical security gaps, this study introduces a comprehensive, multi-layered defense architecture that incorporates recent advancements in Post-Quantum Cryptography (PQC), machine-learning-based Intrusion Detection Systems (IDS), adaptive signal processing techniques, and hardware-oriented countermeasures, informed by 2025 developments in quantum-safe SATCOM.
Keywords: Quantum Machine Learning, Quantum Support Vector Machine (QSVM), Quantum Random Number Generator (QRNG), Satellite Communications Security
Full-Text [PDF 1743 kb]   (15 Downloads)    
Type of Study: Research Paper | Subject: Satellite Communications
Received: 2025/09/07 | Revised: 2026/02/17 | Accepted: 2026/01/27
Rights and permissions
Creative Commons License This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
Creative Commons License
© 2022 by the authors. Licensee IUST, Tehran, Iran. This is an open access journal distributed under the terms and conditions of the Creative Commons Attribution-NonCommercial 4.0 International (CC BY-NC 4.0) license.