Cyber Risk Prediction for UAVs in Space-Related Missions Using Deep Reinforcement Learning

Khosravian, Erfan; Dehghan, Motahareh

doi:10.22034/jsst.2025.1527

Cyber Risk Prediction for UAVs in Space-Related Missions Using Deep Reinforcement Learning

Document Type : Original Research Paper

Authors

Erfan Khosravian ¹

Motahareh Dehghan ²

¹ Department of Mechanical Engineering, Payame Noor University, Tehran, Iran

² Faculty of Industrial and Systems Engineering, Tarbiat Modares University, Tehran, Iran

10.22034/jsst.2025.1527

Abstract

Space exploration and satellite deployment drive modern technological advancements. They are crucial for global communication, navigation, and scientific discovery. Satellites form the backbone of interstellar communication, ensuring reliable data transfer in both civilian and defense sectors. However, as space missions grow more complex, maintaining their integrity and security becomes a major challenge.
Unmanned Aerial Vehicles (UAVs) play a key role in space missions. They assist in satellite deployment, orbital inspections, and inter-satellite communication. Yet, these cyber-physical systems face evolving cybersecurity threats that could jeopardize mission-critical tasks. Traditional intrusion detection systems struggle to counter the complex and dynamic cyber threats targeting UAVs in harsh space environments.
This paper introduces a novel Deep Reinforcement Learning model to predict and mitigate cyber risks in space-related UAV missions. Using a publicly available dataset that combines cyber and physical UAV data, the model predicts multi-step threats such as Denial of Service, Replay, Evil Twin, and False Data Injection. This enables proactive threat mitigation. Compared to traditional machine learning models—Support Vector Machines, Random Forests, and Recurrent Neural Networks—the proposed model achieves superior performance, with 99.34% accuracy and an AUC score of 0.99.

Keywords

Space- related missions

Satellites

Unmanned Aerial Vehicles (UAV)

Cyber Risk Prediction

Deep Reinforcement Learning

Feature Importance

Subjects

Aerospace Engineering

Article Title Persian

Cyber Risk Prediction for UAVs in Space-Related Missions Using Deep Reinforcement Learning

Authors Persian

عرفان خسرویان ¹

مطهره دهقان ²

¹ استادیار، دانشکده مهندسی مکانیک، دانشگاه پیام نور، تهران ایران

² دانشکده مهندسی صنایع و سیستم‌ها، دانشگاه تربیت مدرس، تهران، ایران

Abstract Persian

Keywords Persian

Space- related missions

Satellites

Unmanned Aerial Vehicles (UAV)

Cyber Risk Prediction

Deep Reinforcement Learning

Feature Importance

[1]M. Navabi and F. Malekpour, "Satellite status control using tabulation gain controller in a variable parameter system," Journal of Space Science and Technology, vol. 15, no. 2, pp. 15-25, 2022, (in Persian), https://doi.org/10.30699/jsst.2021.244891.1309.

[2] R. Ghasrizadeh and A. A. Nikkhah, "Improved spoofing loosely coupled INS /GPS with ‎steady state Kalman matrix gain," Journal of Space Science and Technology, vol. 16, no. 3, pp. 37-49, 2023, (in Persian), https://doi.org/10.30699/jsst.2023.1425.

[3] M. Ebrahimi Kachoie, M. Arbabmir, and M. Norouz, "A survey on vision navigation methods for UAV navigation applications," Journal of Space Science and Technology, vol. 10, no. 2, pp. 33-52, 2017, (in Persian).

[4] E. Khosravian and M. Dehghan, "Advancing situation awareness systems: Evaluating decision-making methods with UAV applications," Management Strategies and Engineering Sciences, vol. 6, no. 4, pp. 122-133, 2024, https://doi.org/10.61838/msesj.6.4.13.

[5] C. Rani, H. Modares, R. Sriram, D.Mikulski, and F. l. Lewis, “Security of unmanned aerial vehicle systems against cyber-physical attacks,” The Journal of Defense Modeling and Simulation: Applications, Methodology, Technology, vol. 13, no. 3. pp. 331-342, 2015, https://doi.org/10.1177/1548512915617252.

[6] M. Dehghan and B. Sadeghiyan, "Privacy-preserving collision detection of moving objects," Transactions on Emerging Telecommunications Technologies, vol. 30, no. 3, 2019, Art. no. e3484, https://doi.org/10.1002/ett.3484.

[7] Z. Yu, Z. Wang, J. Yu, D. Liu, H. Herbert Song and Z. Li, "Cybersecurity of unmanned aerial vehicles: a survey," Aerospace and Electronic Systems Magazine, vol. 39, no. 9, pp. 182-215, 2024, https://doi.org/10.1109/MAES.2023.3318226.

[8] S. C. Hassler, U. A. Mughal and M. Ismail, "Cyber-physical intrusion detection system for unmanned aerial vehicles," Transactions on Intelligent Transportation Systems, vol. 25, no. 6, pp. 6106-6117, 2024, https://doi.org/10.1109/TITS.2023.3339728.

[9] M. Dehghan and E. Khosravian, “A review of cognitive UAVs: AI-driven situation awareness for enhanced operations,” AI and Tech in Behavioral and Social Sciences, vol. 2, no. 4, pp. 54-65, 2024, https://doi.org/10.61838/kman.aitech.2.4.6.

[10] B. S. Sarıkaya and Ş. Bahtiyar, "A survey on security of UAV and deep reinforcement learning," Ad Hoc Networks, vol. 164, 2024, Art. no. 103642, https://doi.org/10.1016/j.adhoc.2024.103642.

[11] S. Niyonsaba, K. Konate, and M. M. Soidridine, “Deep learning based intrusion detection for cybersecurity in unmanned aerial vehicles network,” in 4th International Conference on Electrical, Computer and Energy Technologies (ICECE), Sydney, Australia, 2024.

[12] D. Javeed, T. Gao, P. Kumar, S. Shoukat, I. Ahmad and R. Kumar, "An Intelligent and Interpretable Intrusion Detection System for Unmanned Aerial Vehicles," in International Conference on Communications (ICC), Denver, CO, USA, 2024, pp. 1951-1956, https://doi.org/10.1109/ICC51166.2024.10622703.

[13] A. Alzahrani, "Novel approach for intrusion detection attacks on small drones using ConvLSTM model," IEEE Access, vol. 12, pp. 149238-149253, 2024, https://doi.org/10.1109/ACCESS.2024.3471806.

[14] M. Dehghan and E. Khosravian, "Private federated learning for APT detection in internet of drones," Karafan Journal, vol. 20, no. 3, pp. 465-484, 2023, (in Persian), https://doi.org/10.48301/kssa.2023.409787.2649.

[15] M. Rizwanullah et al., “Modelling of metaheuristics with machine learning-enabled cybersecurity in unmanned aerial vehicles" Sustainability, vol. 14, no. 24, 2022, Art. no. 16741, https://doi.org/10.3390/su142416741.

[16] K. Arulkumaran, M. P. Deisenroth, M. Brundage and A. A. Bharath, "Deep Reinforcement Learning: A Brief Survey," Signal Processing Magazine, vol. 34, no. 6, pp. 26-38, 2017, https://doi.org/10.1109/MSP.2017.2743240.

[17] M. Dehghan, B. Sadeghiyan, E. Khosravian, A. S. Moghaddam, and F. Nooshi, “ProAPT: Projection of APT threats with deep reinforcement learning,’ arXiv:2209.07215, 2022, https://doi.org/10.48550/arXiv.2209.07215.

[18] V. François-Lavet, P. Henderson, R. Islam, M. G. Bellemare, and J. Pineau, "An introduction to deep reinforcement learning," Foundations and Trends® in Machine Learning, vol. 11, no. 3-4, pp. 219-354, 2018, http://dx.doi.org/10.1561/2200000071.

[19] Z. Ding, Y. Huang, H. Yuan, and H. Dong, "Introduction to Reinforcement Learning," in Deep Reinforcement Learning: Fundamentals, Research and Applications, H. Dong, Z. Ding, and S. Zhang, Eds. Singapore: Springer Singapore, 2020, pp. 47-123, https://doi.org/10.1007/978-981-15-4095-0_2.

[20] J. S. Bergstra, R. Bardenet, Y. Bengio, and B. Kégl, “Algorithms for hyper-parameter optimization,” in Advances in neural information processing systems24 (NeurIPS 2011), J. Shawe-Taylor, R. Zemel, P. Bartlett, F. Pereira, and K. Weinberger, Eds. Curan Associates, Inc., 2011, pp. 2546-2554.

[21] D. V. Carvalho, E. M. Pereira and J. S. Cardoso, “Machine learning interpretability: A survey on methods and metrics,” Electronics, vol. 8, no. 8, 2019, Art. no. 832, https://doi.org/10.3390/electronics8080832.

[22] M. Saarela and S. Jauhiainen, “Comparison of feature importance measures as explanations for classification models,” SN Applied Sciences, vol. 3, 2021, Art. no. 272, https://doi.org/10.1007/s42452-021-04148-9.