This is an unedited manuscript accepted for publication and provided as an Article in Press for early access at the author’s request. The article will undergo copyediting, typesetting, and galley proof review before final publication. Please be aware that errors may be identified during production that could affect the content. All legal disclaimers of the journal apply.
Heena T Shaikh,
Kazi Kutubuddin Sayyad Liyakat,
- Assistant Professor, Department of Electronics and Telecommunication Engineering, Brahmdevdada Mane Institute of Technology, Solapur, Maharashtra, India
- Professor and Head, Department of Electronics and Telecommunication Engineering, Brahmdevdada Mane Institute of Technology, Solapur, Maharashtra, India
Abstract
The 6G networks bring about new degrees of possible functions related to connectivity, latency, data throughput, and integration with artificial intelligence (AI). This enables advances within healthcare, autonomous systems, and smart cities. The positive impact of rapid advancements must also be balanced with heightened risks due to the sheer volume of gaps that can be exploited, and the complex nature of the alignments and breaches. This results in the breaches being that much more complex to identify. Traditional security mechanisms no longer apply to the highly heterogeneous and dynamic environments present within 6G. This paper focuses on how the application of AI can significantly improve anomaly detection and breach identification in 6G applications. We illustrate an AI-driven, multi-layered framework that combines deep learning, federated learning, and reinforcement learning to behavioral patterns and network risk. AI can monitor complex intrusions and actively mitigate risks. The models can be trained to recognize patterns that deviate in response to events that indicate zero-day attacks, insider threats, and adversarial threats by analyzing large amounts of distributed data. In time, AI processes and models will explain, and improve the gap in latency to address problems of trust and operational feasibility of mission-critical applications. The results demonstrate accurate detection, minimization of false positives, and to demonstrate the transformative potential in securing the next generation of wireless ecosystems within these simulated 6G environments.
Keywords: Artificial Intelligence, 6G, Anomaly Detection, Breach Detection, Zero-Day Attack, Cloud, Internet of Things,
Heena T Shaikh, Kazi Kutubuddin Sayyad Liyakat. A Study on AI-Driven Multi-Layered Defense in 6G Ecosystems. International Journal of Radio Frequency Innovations. 2026; 04(01):-.
Heena T Shaikh, Kazi Kutubuddin Sayyad Liyakat. A Study on AI-Driven Multi-Layered Defense in 6G Ecosystems. International Journal of Radio Frequency Innovations. 2026; 04(01):-. Available from: https://journals.stmjournals.com/ijrfi/article=2026/view=244097
References
1. Haque ME, Tariq F, Khandaker MR, Wong KK, Zhang Y. A survey of scheduling in 5G URLLC and outlook for emerging 6G systems. IEEE access. 2023 Apr 5;11:34372-96.
2. Xu Y, Xu G, Ma C, An Z. An advancing temporal convolutional network for 5G latency services via automatic modulation recognition. IEEE Transactions on Circuits and Systems II: Express Briefs. 2022 Feb 18;69(6):3002-6.
3. Mukherjee M, Guo M, Lloret J, Zhang Q. Leveraging intelligent computation offloading with fog/edge computing for tactile internet: Advantages and limitations. IEEE Network. 2020 Aug 12;34(5):322-9.
4. Crysovergis I, Trevlakis SE, Kleitsas D, Boulogeorgos AA, Tsiftsis TA, Niyato D. A Digital Twin Based Reconfigurable Intelligent Surface Phase Adaptation Using Spiking Reinforcement Learning Policy Optimization. In2025 IEEE International Conference on Machine Learning for Communication and Networking (ICMLCN) 2025 May 26 (pp. 1- 7). IEEE.
5. Nakao M, Sakai M, Hanada Y, Murai H, Sato M. Graph optimization algorithm for low- latency interconnection networks. Parallel Computing. 2021 Sep 1;106:102805.
6. Li B, Battiti R, Fang Y. Achieving optimal performance by using the IEEE 802.11 MAC protocol with service differentiation enhancements. IEEE Transactions on Vehicular Technology. 2007 May 15;56(3):1374-87.
7. Wang Z, Zhou Y, Zou Y, An Q, Shi Y, Bennis M. A graph neural network learning approach to optimize RIS-assisted federated learning. IEEE Transactions on Wireless Communications. 2023 Jan 30;22(9):6092-106.
8. Zeng Z, Han C, Björnson E. Physics-Informed Spatial-Temporal Transformer for Terahertz Near-Field Beam Tracking. arXiv preprint arXiv:2603.16251. 2026 Mar 17.
9. Silitonga JL. A review of AI-driven predictive maintenance in telecommunications. International Journal of Information System and Innovative Technology. 2024 Dec 30;3(2):25-31.
10. Chabira C, Shayea I, Nurzhaubayeva G, Aldasheva L, Yedilkhan D, Amanzholova S. AI- driven handover management and load balancing optimization in ultra-dense 5G/6G cellular networks. Technologies. 2025 Jul 1;13(7):276.
11. Liyakat KK. Machine learning approach using artificial neural networks to detect malicious nodes in IoT networks. InInternational Conference on Machine Learning, IoT and Big Data 2023 Mar 10 (pp. 123-134). Singapore: Springer Nature Singapore.
12. Azman F, Suraya Q, Rahim FA, Mohd MS, Ariffin NA. My guardian: A personal safety mobile application. In2018 IEEE Conference on Open Systems (ICOS) 2018 Nov 21 (pp. 37-41). IEEE.
13. Chaturvedi SK, Venu N. AI-Enabled Multi-Layer Security for 5G Network Slicing: Performance Analysis and Optimization. In2025 IEEE International Conference on Communication Networks and Computing (CNC) 2025 Dec 29 (pp. 211-217). IEEE.
International Journal of Radio Frequency Innovations
| Volume | 04 |
| 01 | |
| Received | 13/05/2026 |
| Accepted | 14/05/2026 |
| Published | 16/05/2026 |
| Publication Time | 3 Days |
Login
PlumX Metrics