GAME-THEORETIC AND REINFORCEMENT LEARNING-BASED ALGORITHM FOR INTENTIONAL JAMMING MITIGATION
Abstract
Intentional jamming represents a serious threat to the security and availability of wireless communication systems. Modern wireless networks, including cognitive radio, sensor networks, and Internet of Things infrastructures, are particularly vulnerable because adversaries can dynamically adapt their jamming strategies. The objective of this study is to develop an adaptive anti-jamming algorithm capable of maintaining communication reliability under dynamic interference conditions. To achieve this goal, the interaction between the legitimate transmitter and the jammer is modeled as a Markov Stackelberg game, where the legitimate node acts as a leader and the jammer acts as a follower. Reinforcement learning is used to determine the optimal strategy of the leader in a stochastic environment, while robustness against channel uncertainty is ensured through a SOCP (Second-order cone programming) formulation that guarantees the required quality-of-service constraints. The learning process is implemented using the SAC (Soft Actor-Critic) algorithm, which enables stable policy optimization in continuous action spaces and stochastic environments. The research tasks include the formalization of the anti-jamming interaction as a Markov decision process, the integration of reinforcement learning with a robust SOCP optimization layer, and the evaluation of the proposed approach through simulation. A Monte Carlo simulation of the proposed algorithm, as well as several algorithms based on FHSS (Frequency-Hopping Spread Spectrum), was conducted. The proposed anti-jamming algorithm reduces the probability of communication outage by 0.14. The results indicate that the proposed approach improves the resilience of wireless communication systems and reduces the probability of successful denial-of-service attacks at the physical layer
References
1. Xiao Y., Ren H., Wu S., Liu L., Meng X., Ding P. Anti-Jamming Method of Cognitive Radio Based on Q-Learning, Proceedings of the 12th International Conference on Electronics, Communications and Networks (CECNet 2022). Frontiers in Artificial Intelligence and Applications, 2022, Vol. 363,
pp. 97-104. DOI: 10.3233/FAIA220523 (accessed 09 March 2026).
2. Zumegen F.J., Jain I.K., Bharadia D. BeamArmor: Seamless Anti-Jamming in 5G Cellular Networks with MIMO Null-Steering, Proceedings of the 25th International Workshop on Mobile Computing Sys-tems and Applications (HotMobile ’24). New York: Association for Computing Machinery, 2024, pp. 121-126. DOI: 10.1145/3638550.3641138 (accessed 09 March 2026).
3. Andrei V.C., Djuhera A., Li X., Mönich U.J., Boche H., Saad W. Resilient-by-Design Framework for MIMO-OFDM Communications under Smart Jamming. – 2024. – URL: https://rosap.ntl.bts.gov/ view/dot/80055 (accessed 09 March 2026).
4. Jia L., Qi N., Chu F., Fang S., Wang X., Ma S., Feng S. Game-Theoretic Learning Anti-Jamming Ap-proaches in Wireless Networks, IEEE Communications Magazine, 2022, Vol. 60, pp. 60-66. DOI: 10.1109/MCOM.001.00496.
5. Han C., Huo L., Tong X., Wang H., Liu X. Spatial Anti-Jamming Scheme for Internet of Satellites Based on the Deep Reinforcement Learning and Stackelberg Game, IEEE Transactions on Vehicular Technol-ogy, 2020, Vol. 69, pp. 5331-5342. DOI: 10.1109/TVT.2020.2982672.
6. Aref M., Jayaweera S., Yepez E. A Survey on Cognitive Anti-Jamming Communications, IET Commu-nications, 2020, Vol. 14, No. 18, pp. 3111-3127. DOI: 10.1049/iet-com.2020.0024.
7. Imran M., Pan Z., Liu N., Sajjad M., Butt F. Anti-Jamming for Cognitive Radio Networks with Stackel-berg Game-Assisted DSSS Approach, EURASIP Journal on Wireless Communications and Network-ing, 2024, Vol. 2024, pp. 1-18. DOI: 10.1186/s13638-024-02397-x.
8. Liu L., Pu W., Li Y., Luo Z.-Q. Learning an Opponent-Aware Anti-Jamming Strategy via Online Con-vex Optimization, arXiv, 2026. arXiv:2604.11016. DOI: 10.48550/arXiv.2604.11016.
9. Liu L., Pu W., Li Y., Jiu B., Luo Z.-Q. Radar Anti-Jamming Strategy Learning via Domain-Knowledge Enhanced Online Convex Optimization, arXiv, 2024. arXiv:2402.16274. DOI: 10.48550/arXiv.2402.16274.
10. Chen S., Tu W.-W., Zhao P., Zhang L. Optimistic Online Mirror Descent for Bridging Stochastic and Adversarial Online Convex Optimization, Proceedings of the 40th International Conference on Machine Learning (ICML). Proceedings of Machine Learning Research, 2023, Vol. 202, pp. 5002-5035. Avail-able at: https://proceedings.mlr.press/v202/chen23aa.html (accessed 22 June 2026).
11. Yao F., Jia L. A Collaborative Multi-Agent Reinforcement Learning Anti-Jamming Algorithm in Wire-less Networks, arXiv, 2018. arXiv:1809.04374. DOI: 10.48550/arXiv.1809.04374.
12. Joulani P., Gyorgy A., Szepesvari C. Delay-Tolerant Online Convex Optimization: Unified Analysis and Adaptive-Gradient Algorithms, Proceedings of the AAAI Conference on Artificial Intelligence, 2016, Vol. 30, pp. 1744-1750. DOI: 10.1609/aaai.v30i1.10320.
13. Chen Y., Zhao Z. Intelligent Anti-Jamming Decision Algorithm of Bivariate Frequency Hopping Pattern Based on ET-PPO, Telecommunications Science, 2022, Vol. 38, pp. 1-13. DOI: 10.11959/j.issn.1000-0801.2022264.
14. Feng X., Niu Y., Liu Q., Zhou Q. Decision Making for Communication Anti-Jamming Tasks with Knowledge-Graph-Based Q-Learning, Electronics, 2024, Vol. 13, Art. 4757. DOI: 10.3390/ electron-ics13234757.
15. Chang X., Li Y., Zhao Y., Du Y., Liu D. An Improved Anti-Jamming Method Based on Deep Rein-forcement Learning and Feature Engineering, IEEE Access, 2022, Vol. 10, pp. 69992-70000. DOI: 10.1109/ACCESS.2022.3187030.
16. Xu J., Lou H., Zhang W., Sang G. An Intelligent Anti-Jamming Scheme for Cognitive Radio Based on Deep Reinforcement Learning, IEEE Access, 2020, Vol. 8, pp. 202563-202572. DOI: 10.1109/ ACCESS.2020.3036027.
17. Ali A., Naser S., Muhaidat S. Defeating Proactive Jammers Using Deep Reinforcement Learning for Resource-Constrained IoT Networks, arXiv, 2023. arXiv:2307.06796. DOI: 10.48550/arXiv.2307.06796.
18. Li X., Chen J., Ling X., Wu T. Deep Reinforcement Learning-Based Anti-Jamming Algorithm Using Dual Action Network, IEEE Transactions on Wireless Communications, 2023, Vol. 22, pp. 5403-5418. DOI: 10.1109/TWC.2022.3227575.
19. Tang X., Jiang Y., Liu J., Du Q., Niyato D., Han Z. Deep Learning-Assisted Jamming Mitigation with Movable Antenna Array, arXiv, 2024. arXiv:2410.20344. DOI: 10.48550/arXiv.2410.20344.
20. Goldsmith A. Wireless Communications. Cambridge: Cambridge University Press, 2005, 584 p.
21. Cheng L., Xu Z., Zhou J., Tian D., Duan X., Qu K., Zhao D. Adaptive Spectrum Anti-Jamming in UAV-Enabled Air-to-Ground Networks: A Bimatrix Stackelberg Game Approach, Electronics, 2023, Vol. 12, Art. 4344. DOI: 10.3390/electronics12204344.
22. Noori H., Vilni S. Jamming and Anti-Jamming in Interference Channels: A Stochastic Game Approach, IET Communications, 2020, Vol. 14, pp. 682-692. DOI: 10.1049/iet-com.2019.0637.
