A Deep Neural Network Assisted Physical Layer Security Mechanism for Wireless Networks

Abstract

The physical layer in wireless systems is inherently susceptible to eavesdropping, jamming, spoofing, and signal injection attacks because wireless signals propagate through open space. Unlike wired networks, where physical access is more controlled, wireless communication can be intercepted by any nearby device. Attackers can exploit features such as channel reciprocity, power control, or modulation characteristics to compromise communications. These vulnerabilities make it imperative to secure the physical layer, especially in applications involving sensitive data like military, healthcare, and IoT-based services, which rely primarily on wireless data transmission. This paper presents a machine learning assisted security aware channel assignment protocol against possible adversarial eavesdropping attacks. The ML parameters such as gradient, iterations to convergence and cost function have been computed and presented. The final error rate with and without the proposed system under adversarial attacks is also presented. It can be observed that the proposed approach is close to the no adversarial attack condition clearly indicating the efficacy of the approach to proactively thwart potential attacks. The error rates are also significantly lower than existing approach in the domain. Additionally, to enhance the QoS of the system, a handoff mechanism is also proposed in conjugation with equalization. The metrics for evaluation of the performance of the system are the BER, scatter and MSE.

Introduction

With the emergence of deep learning and quantum computing, traditional network security methods are becoming vulnerable. This is prompting a shift toward a layered security model based on the OSI model, incorporating defenses at the physical, network, and application layers.

1. Physical Layer Security (PLS):

• PLS is essential in wireless networks, where open transmission makes them vulnerable to eavesdropping and interference.

• A security-aware eavesdropping rejection mechanism is proposed using channel frequency response analysis and discrete equalization to recover lost data.

2. Cognitive Wireless Networks (CWNs):

• CWNs use AI and machine learning (ML) to dynamically manage spectrum use.

• These networks face unique security threats like spectrum sensing data falsification, denial of service, and eavesdropping.

• Spectrum sensing and channel state information (CSI) are key to detecting attacks but are challenged by noise, mobility, and dynamic channel conditions.

3. ML-Assisted Security:

• ML techniques (e.g., supervised learning, clustering, neural networks) help in:

  • Detecting anomalous behavior (intrusion detection)

  • Enhancing spectrum sensing accuracy

  • Predicting network conditions

• A security-aware channel assignment algorithm is developed using a deep neural network trained on pilot signals, time samples, and SINR.

4. Attack Detection and Mitigation:

• Attacks are categorized into low, moderate, and high eavesdropping, affecting CSI.

• The proposed system uses threshold-based detection to determine whether a collision (attack) is occurring.

• False alarms may occur due to noise being misinterpreted as malicious activity.

5. Algorithm Implementation:

• A multi-step ML algorithm is described:

  • Training with noisy data

  • Using least squares cost minimization

  • Dynamically updating weights

  • Making real-time secure channel assignment decisions based on CSI

• This helps adapt the network to different attack levels and maintain performance.

6. Collaborative Security and Future Trends:

• Cross-layer collaboration and trust management frameworks are essential for secure CWNs.

• Future work focuses on:

  • Lightweight, adaptive ML models

  • Federated and transfer learning

  • Addressing privacy and fairness concerns

Conclusion

It can be concluded that Physical Layer Security is an essential aspect in the context of wireless networks, offering a foundational and complementary layer of protection against emerging threats. By capitalizing on the unique characteristics of wireless channels, PLS provides efficient and robust security, particularly in environments where traditional methods fall short. As wireless communication continues to underpin critical applications, the importance of integrating physical layer security across network design and implementation becomes not only beneficial but imperative. The ability of ML models to learn from data and adapt to changing environments makes them indispensable for the efficient and reliable operation of CWNs. As research and technology continue to advance, the integration of more sophisticated ML techniques will further enhance the capabilities and resilience of cognitive wireless networks, paving the way for smarter and more adaptive wireless communication systems. The proposed approach uses a machine learning based security aware channel assignment protocol for thwarting potential adversarial attacks. The proposed approach attains fast convergence at low BER rates, thereby rendering high improved security. Additionally, the handoff also improves the QoS of the system under variable channel conditions encountering attacks.

References

[1] SK Singh, S Kumar, A Chhabra, A Sharma, “Advancements in secure quantum communication and robust key distribution techniques for cybersecurity applications”, Cyber Security and Applications, Elsevier 2025, 100089. [2] K. St. Germain and F. Kragh, “Physical Layer Authentication Using Channel State Information and Machine Learning,” IEEE, Jun. 2020. [3] A. Senigagliesi, L. Baldi and E. Gambi, “Performance of Statistical and Machine Learning Techniques for Physical Layer Authentication,” arXiv, 2020. [4] A. Albehadili et al., “Machine Learning Based PHY Authentication for Mobile OFDM Transceivers,” in Proc. IEEE VTC 2020 Fall, 2020. [5] G. Gao, N. Ni, D. Feng, X. Jing and Y. Cao, “Physical Layer Authentication Under Intelligent Spoofing in Wireless Sensor Networks,” Signal Processing, vol.?166, 2020. [6] L. Liao et al., “Multiuser Physical Layer Authentication in Internet of Things with Data Augmentation,” IEEE Internet of Things J., vol.?7, no.?3, pp.?2077–2088, Mar.?2020. [7] H. Fang, X. Wang, Z. Xiao and L. Hanzo, “Autonomous Collaborative Authentication with Privacy Preservation in 6G: From Homogeneity to Heterogeneity,” IEEE Network, vol.?36, no.?6, pp.?28–36, Jul.?2022. [8] R. Xie et al., “A Generalizable Model and Data Driven Approach for Open Set RFF Authentication,” IEEE Trans. Inf. Forensics Security, vol.?16, pp.?4435–4450, Aug.?2021. [9] A Soni, R Upadhyay, A Jain “Internet of Things and wireless physical layer security: A survey”, Computer Communication, Networking and Internet Security, Springer 2017, pp.115-123. [10] https://certera.com/blog/what-is-the-osi-model-layers-benefits-and-applications/ [11] S. Sullivan, A. Brighente, S. A. P. Kumar and M. Conti, \"5G Security Challenges and Solutions: A Review by OSI Layers,\" in IEEE Access, vol. 9, pp. 116294-116314, 2021 [12] X. Zeng, C. Wang and Z. Li, “CVCA: A Complex Valued Classifiable Autoencoder for mmWave Massive MIMO Physical Layer Authentication,” presented at IEEE INFOCOM Workshops, 2023 [13] AA Sharifi, M Sharifi, MJM Niya, “Secure cooperative spectrum sensing under primary user emulation attack in cognitive radio networks: Attack-aware threshold selection approach”, vol.70, issue.1, Elsevier 2020. [14] Syed Hashim Raza Bukhari ,Sajid Siraj,Mubashir Husain Rehmani,“ NS-2 based simulation framework for cognitive radio sensor networks”, SPRINGER 2019/. [15] K. J. Prasanna Venkatesan ,V. Vijayarangan, “Secure and reliable routing in cognitive radio networks”, SPRINGER 2018. [16] K Gai ,Meikang Qiu ,Hui Zhao, “Security-Aware Efficient Mass Distributed Storage Approach for Cloud Systems in Big Data”,IEEE 2017. [17] Ju Ren ,Yaoxue Zhang ,Qiang Ye , Kan Yang ; Kuan Zhang ,Xuemin Sherman Shen,” Exploiting Secure and Energy-Efficient Collaborative Spectrum Sensing for Cognitive Radio Sensor Networks”, IEEE 2016. [18] R.K. Sharma ;,Danda B. Rawat,” Advances on Security Threats and Countermeasures for Cognitive Radio Networks: A Survey”,IEEE [19] A. Khamaiseh, I. Alsmadi, and A. Al Alaj, “Deceiving Machine Learning based Saturation Attack Detection Systems in SDN,” in Proc. IEEE NFV SDN, 2020. [20] M. Assis, L. F. Carvalho, J. Lloret, and M. L. Proença Jr., “A GRU Deep Learning System Against Attacks in Software Defined Networks,” J. Network and Computer Applications, vol.?177, p.?102942, 2021. [21] J. Bhayo et al., “A Time Efficient Approach Toward DDoS Attack Detection in IoT Network Using SDN,” IEEE Internet of Things J., vol.?9, no.?5, pp.?3612–3630, Mar.?2022. [22] A. Bahashwan, M. Anbar, S. Manickam, T. Al Amiedy, M. Aladaileh, and I. H. Hasbullah, “A Systematic Literature Review on Machine Learning and Deep Learning Approaches for Detecting DDoS Attacks in Software Defined Networking,” Sensors, vol.?23, no.?9, p.?4441, May?2023. ijisae.org. [23] N. Niknami and J. Wu, “Advanced ML/DL?Based Intrusion Detection Systems for Software?Defined Networks, in Network Security Empowered by Artificial Intelligence, Y. Chen et al., Eds., Adv. in Inf. Security, vol.?107, Springer, Cham, pp.?59-84, Feb.2024. [24] C. Zhao et al., \"Generative AI for Secure Physical Layer Communications: A Survey,\" in IEEE Transactions on Cognitive Communications and Networking, vol. 11, no. 1, pp. 3-26, Feb. 2024. [25] B. Ozpoyraz, A. T. Dogukan, Y. Gevez, U. Altun and E. Basar, \"Deep Learning-Aided 6G Wireless Networks: A Comprehensive Survey of Revolutionary PHY Architectures,\" in IEEE Open Journal of the Communications Society, vol. 3, pp. 1749-1809, 2022 [26] M. S. Elsayed, N.-A. Le-Khac, S. Dev, and A. D. Jurcut, “DDoSNet: A Deep?Learning Model for Detecting Network Attacks,” in Proc. IEEE 21st WoWMoM, Aug.?2020 [27] N. Abuzainab, M. Alrabeiah, A. Alkhateeb and Y. E. Sagduyu, \"Deep Learning for THz Drones with Flying Intelligent Surfaces: Beam and Handoff Prediction,\" 2021 IEEE International Conference on Communications Workshops (ICC Workshops), Montreal, QC, Canada, 2021, pp. 1-6. [28] S. Alraih, R. Nordin, A. Abu-Samah, I. Shayea and N. F. Abdullah, \"A Survey on Handover Optimization in Beyond 5G Mobile Networks: Challenges and Solutions,\" in IEEE Access, vol. 11, pp. 59317-59345, 2023 [29] Ara and B. Kelley, \"Physical Layer Security for 6G: Toward Achieving Intelligent Native Security at Layer-1,\" in IEEE Access, 2024, vol. 12, pp. 82800-82824. [30] T. N. Nguyen et al., \"Cooperative Satellite-Terrestrial Networks With Imperfect CSI and Multiple Jammers: Performance Analysis and Deep Learning Evaluation,\" in IEEE Systems Journal, vol. 18, no. 4, pp. 2062-2073, Dec. 2024, [31] A. Tusha, S. Do?an and H. Arslan, \"A Hybrid Downlink NOMA With OFDM and OFDM-IM for Beyond 5G Wireless Networks,\" in IEEE Signal Processing Letters, 2020, vol. 27, pp. 491-495

Copyright

Copyright © 2025 Vinit Kumar Singh, Dr. Ranu Pandey. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.