6G THz Ağlarında Açıklanabilir ve Güvenilir Yapay Zeka: Zorluklar, Çözüm Yaklaşımları ve Gelecek Perspektifleri

Year 2025, Volume: 2 Issue: 2, 61 - 80, 30.09.2025

Amine Gonca Toprak , Öykü Berfin Mercan , Yasin Emre Tok , Sümeye Nur Karahan

Abstract

6G Terahertz (THz) haberleşme teknolojileri, yüksek veri iletim hızları, ultra düşük gecikme süresi ve yoğun bağlantı kapasitesi sunarak gelecek nesil kablosuz iletişim ağlarının temel yapı taşlarından biri olarak öne çıkmaktadır. Bu ağların yüksek performanslı, dinamik ve esnek bir şekilde yönetilmesinde yapay zekâ (YZ) hayati bir rol üstlenmektedir. Ancak YZ modelleri, karar alma süreçlerinin opak yapısı nedeniyle özellikle güvenlik, şeffaflık ve güvenilirlik açısından önemli zorluklar barındırmaktadır. Bu derleme çalışması, 6G THz ağları için özelleştirilmiş Açıklanabilir Yapay Zekâ (XAI) ve Güvenilir Yapay Zekâ (Trustworthy AI) yaklaşımlarını kapsamlı bir şekilde incelemektedir. Çalışma, hüzmeleme, kaynak tahsisi ve kanal modelleme gibi temel kullanım senaryolarında YZ’nin rolünü değerlendirerek başlamaktadır. Ardından, SHAP (SHapley Additive exPlanations), LIME (Local Interpretable Model-Agnostic Explanations) ve dikkat (attention) tabanlı görselleştirme gibi yaygın XAI teknikleri ele alınmakta ve bu yöntemlerin karmaşık ağ mimarilerinde uygulanabilirliği tartışılmaktadır. Bununla birlikte, düşman saldırılar (adversarial attacks), veri zehirleme (data poisoning) ve mahremiyet ihlalleri gibi kritik güvenlik tehditleri incelenmekte; model dayanıklılığı ve hesap verebilirliğini artırmaya yönelik mevcut çözüm önerileri değerlendirilmektedir. Son olarak, performans–açıklanabilirlik dengesi ile ilişkili temel zorluklar tanımlanmakta ve 6G ağlarında güvenli, şeffaf ve regülasyonlarla uyumlu YZ sistemlerinin geliştirilmesine yönelik gelecek araştırma alanları ortaya konulmaktadır.

Keywords

6G THz ağlar , açıklanabilir yapay zeka (XAI) , güvenilir yapay zeka , yeni nesil kablosuz ağlar

Supporting Institution

The Scientific and Technological Research Council of Türkiye (TÜBİTAK)

Project Number

5249902

Thanks

This work is supported by The Scientific and Technological Research Council of Türkiye (TÜBİTAK) 1515 Frontier R&D Laboratories Support Program for Türk Telekom 6G R&D Lab under project number 5249902.

Explainable and Trustworthy Artificial Intelligence in 6G THz Networks: Challenges, Solutions, and Future Perspectives

Abstract

6G Terahertz (THz) communication technologies are emerging as one of the fundamental cornerstones of next-generation wireless networks, offering high data transmission speeds, ultra-low latency, and dense connectivity. Artificial intelligence (AI) plays a critical role in managing these networks in a high-performance, dynamic, and flexible manner. However, AI models pose significant challenges, especially regarding security, transparency and reliability, due to their opaque decision-making processes. This review provides a comprehensive examination of Explainable Artificial Intelligence (XAI) and Trustworthy AI approaches tailored for 6G THz networks. The study begins by evaluating the role of AI in key use cases such as beamforming, resource allocation, and channel modeling. Then it explores popular XAI techniques, including SHAP(SHapley Additive exPlanations), LIME (Local Interpretable Model-Agnostic Explanations), and attention-based visualization, and discusses their applicability within complex network architectures. Moreover, it investigates critical security threats, such as adversarial attacks, data poisoning, and privacy breaches, and reviews existing solutions aimed at enhancing model robustness and accountability. Finally, this work identifies key challenges associated with the performance-explainability trade-off and outlines promising directions for future research in the development of secure, transparent, and regulation-compliant AI systems for 6G networks.

Keywords

6G THz networks , explainable artificial intelligence (XAI) , trustworthy artificial intelligence , next generation wireless networks

Supporting Institution

The Scientific and Technological Research Council of Türkiye (TÜBİTAK)

Project Number

5249902

Thanks

This work is supported by The Scientific and Technological Research Council of Türkiye (TÜBİTAK) 1515 Frontier R&D Laboratories Support Program for Türk Telekom 6G R&D Lab under project number 5249902.

References

• A. A. A. Solyman and K. Yahya, “Evolution of wireless communication networks: From 1g to 6g and future perspective,” International Journal of Electrical and Computer Engineering (IJECE), vol. 12, no. 4, pp. 3943–3950, 2022, ISSN: 2722-2578. DOI: 10.11591/ijece.v12i4.pp3943-3950. [Online]. Available: https://ijece.iaescore.com/index.php/IJECE/article/view/27115.
• B. Bakare and E. Bassey, “A comparative study of the evolution of wireless communication technologies from the first generation (1g) to the fourth generation (4g),” Int J Elect Commun Comp Eng, vol. 12, no. 3, pp. 73–84, 2021, ISSN: 2249–071X. [Online]. Available: https://www.ijecce.org/index.php/issues?view=publication&task=show&id=1366.
• R. Agrawal, “Comparison of different mobile wireless technology (from 0g to 6g),” ECS Transactions, vol. 107, no. 1, p. 4799, 2022. DOI: 10.1149/10701.4799ecst.
• C. Yeh, G. D. Jo, Y.-J. Ko, and H. K. Chung, “Perspectives on 6g wireless communications,” ICT Express, vol. 9, no. 1, pp. 82–91, 2023, ISSN: 2405-9595. DOI: https://doi.org/10.1016/j.icte.2021.12.017. [Online]. Available: https://www.sciencedirect.com/science/article/pii/S240595952100182X.
• Y. Zuo, J. Guo, N. Gao, Y. Zhu, S. Jin, and X. Li, “A survey of blockchain and artificial intelligence for 6g wireless communications,” IEEE Communications Surveys Tutorials, vol. 25, no. 4, pp. 2494–2528, 2023. DOI: 10.1109/COMST.2023.3315374.
• N. Kaur and L. Gupta, “Securing the 6g–iot environment: A framework for enhancing transparency in artificial intelligence decision-making through explainable artificial intelligence,” Sensors, vol. 25, no. 3, 2025, ISSN: 1424-8220. DOI: 10.3390/s25030854. [Online]. Available: https://www.mdpi.com/1424-8220/25/3/854.
• Q. Xue et al., “A survey of beam management for mmwave and thz communications towards 6g,” IEEE Communications Surveys Tutorials, vol. 26, no. 3, pp. 1520–1559, 2024. DOI: 10.1109/COMST.2024.3361991.
• S. Liu, X. Yu, R. Guo, Y. Tang, and Z. Zhao, “Thz channel modeling: Consolidating the road to thz communications,” China Communications, vol. 18, no. 5, pp. 33–49, 2021. DOI: 10.23919/JCC.2021.05.003.
• K. Strecker, S. Ekin, and J. F. O’Hara, “Fundamental performance limits on terahertz wireless links imposed by group velocity dispersion,” IEEE Transactions on Terahertz Science and Technology, vol. 12, no. 1, pp. 87–97, 2022. DOI: 10.1109/TTHZ.2021.3127151.
• R. Chataut, M. Nankya, and R. Akl, “6g networks and the ai revolution—exploring technologies, applications, and emerging challenges,” Sensors, vol. 24, no. 6, 2024, ISSN: 1424-8220. DOI: 10.3390/s24061888. [Online]. Available: https://www.mdpi.com/1424-8220/24/6/1888.
• J. M. J. Huttunen, D. Korpi, and M. Honkala, “Deeptx: Deep learning beamforming with channel prediction,” IEEE Transactions on Wireless Communications, vol. 22, no. 3, pp. 1855–1867, 2023. DOI: 10.1109/TWC.2022.3207055.
• S. Wang, M. A. Qureshi, L. Miralles-Pechuán, T. Huynh-The, T. R. Gadekallu, and M. Liyanage, “Explainable ai for 6g use cases: Technical aspects and research challenges,” IEEE Open Journal of the Communications Society, vol. 5, pp. 2490–2540, 2024. DOI: 10.1109/OJCOMS.2024.3386872.
• R. Dwivedi et al., “Explainable ai (xai): Core ideas, techniques, and solutions,” ACM Comput. Surv., vol. 55, no. 9, Jan. 2023, ISSN: 0360-0300. DOI: 10.1145/3561048. [Online]. Available: https://doi.org/10.1145/3561048.
• İ. Kök, F. Y. Okay, Ö. Muyanlı, and S. Özdemir, “Explainable artificial intelligence (xai) for internet of things: A survey,” IEEE Internet of Things Journal, vol. 10, no. 16, pp. 14 764–14 779, 2023. DOI: 10.1109/JIOT.2023.3287678.
• H. Sun et al., “Advancing 6g: Survey for explainable ai on communications and network slicing,” IEEE Open Journal of the Communications Society, vol. 6, pp. 1372–1412, 2025. DOI: 10.1109/OJCOMS.2025.3534626.
• N. Khan, S. Coleri, A. Abdallah, A. Celik, and A. M. Eltawil, “Explainable and robust artificial intelligence for trustworthy resource management in 6g networks,” IEEE Communications Magazine, vol. 62, no. 4, pp. 50–56, 2024. DOI: 10.1109/MCOM.001.2300172.
• V. Chamola, V. Hassija, A. R. Sulthana, D. Ghosh, D. Dhingra, and B. Sikdar, “A review of trustworthy and explainable artificial intelligence (xai),” IEEE Access, vol. 11, pp. 78 994–79 015, 2023. DOI: 10.1109/ACCESS.2023.3294569.
• N. Kaur and L. Gupta, An approach to enhance iot security in 6g networks through explainable ai, 2024. arXiv: 2410.05310 [cs.CR]. [Online]. Available: https://arxiv.org/abs/2410.05310.
• S. Garg, K. Kaur, G. S. Aujla, G. Kaddoum, P. Garigipati, and M. Guizani, “Trusted explainable ai for 6g-enabled edge cloud ecosystem,” IEEE Wireless Communications, vol. 30, no. 3, pp. 163–170, 2023. DOI: 10.1109/MWC.016.220047.
• A. Nechi et al., “Practical trustworthiness model for dnn in dedicated 6g application,” in 2023 19th International Conference on Wireless and Mobile Computing, Networking and Communications (WiMob), 2023, pp. 312–317. DOI: 10.1109/WiMob58348.2023.10187759.
• W. Guo, “Explainable artificial intelligence for 6g: Improving trust between human and machine,” IEEE Communications Magazine, vol. 58, no. 6, pp. 39–45, 2020. DOI: 10.1109/MCOM.001.2000050.
• I. Update, “Ericsson mobility report,” Ericsson, Stockholm, Sweden, Technical Report, 2013. [Online]. Available: https://images.youmark.it/wp-content/uploads/2013/09/24081357/emraugust-20131.pdf.
• X. You, C.-X. Wang, J. Huang, et al., “Towards 6g wireless communication networks: Vision, enabling technologies, and new paradigm shifts,” Science China Information Sciences, vol. 64, p. 110 301, 2021. DOI: 10.1007/s11432-020-2955-6.
• W. Yu et al., Ai and deep learning for thz ultra-massive mimo: From model-driven approaches to foundation models, 2025. arXiv: 2412.09839 [eess.SP]. [Online]. Available: https://arxiv .org/abs/2412.09839.
• S. Ali et al., “6g white paper on machine learning in wireless communication networks,” CoRR, vol. abs/2004.13875, 2020. arXiv: 2004.13875. [Online]. Available: https://arxiv.org/abs/2004.13875.
• Y. Zhang, M. Alrabeiah, and A. Alkhateeb, “Reinforcement learning of beam codebooks in millimeter wave and terahertz mimo systems,” IEEE Transactions on Communications, vol. 70, no. 2, pp. 904–919, 2022. DOI: 10.1109/TCOMM.2021.3126856.
• M. Alrabeiah and A. Alkhateeb, “Deep learning for mmwave beam and blockage prediction using sub-6 ghz channels,” IEEE Transactions on Communications, vol. 68, no. 9, pp. 5504–5518, 2020. DOI: 10.1109/TCOMM.2020.3003670.
• J. Zhang, G. Zheng, Y. Zhang, I. Krikidis, and K.-K. Wong, “Deep learning based predictive beamforming design,” IEEE Transactions on Vehicular Technology, vol. 72, no. 6, pp. 8122–8127, 2023. DOI: 10.1109/TVT.2023.3238108.
• Z. Hu, Y. Li, and C. Han, “Transfer learning enabled transformer-based generative adversarial networks for modeling and generating terahertz channels,” Communications Engineering, vol. 3, p. 153, 2024. DOI: 10.1038/s44172-024-00309-x.
• A. Nouruzi et al., Toward a smart resource allocation policy via artificial intelligence in 6g networks: Centralized or decentralized? 2022. arXiv: 2202.09093 [eess.SP]. [Online]. Available: https://arxiv.org/abs/2202.09093.
• A. Patil, S. Iyer, and R. J. Pandya, A survey of machine learning algorithms for 6g wireless networks, 2022. arXiv: 2203.08429 [cs.NI]. [Online]. Available: https://arxiv.org/abs/2203.08429.
• Q. Wu, S. Zhang, B. Zheng, C. You, and R. Zhang, “Intelligent reflecting surface-aided wireless communications: A tutorial,” IEEE Transactions on Communications, vol. 69, no. 5, pp. 3313–3351, 2021. DOI: 10.1109/TCOMM.2021.3051897.
• Y. E. Tok and A. M. Demirtaş, “Optimizing intelligent reflecting surfaces with discrete phase shifts and pilot overhead reduction using deep learning,” in 2024 IEEE International Black Sea Conference on Communications and Networking (BlackSeaCom), 2024, pp. 292–295. DOI: 10.1109/BlackSeaCom61746.2024.10646214.
• A. Faisal, I. Al-Nahhal, O. A. Dobre, and T. M. N. Ngatched, “Deep reinforcement learning for ris-assisted fd systems: Single or distributed ris?” IEEE Communications Letters, vol. 26, no. 7, pp. 1563–1567, Jul. 2022, ISSN: 2373-7891. DOI: 10.1109/lcomm.2022.3170061. [Online]. Available: http://dx.doi.org/10.1109/LCOMM.2022.3170061.
• M. A. S. Sejan, M. H. Rahman, B.-S. Shin, J.-H. Oh, Y.-H. You, and H.-K. Song, “Machine learning for intelligent-reflecting-surface-based wireless communication towards 6g: A review,” Sensors, vol. 22, no. 14, 2022, ISSN: 1424-8220. DOI: 10.3390/s22145405. [Online]. Available: https://www.mdpi.com/1424-8220/22/14/5405.
• R. Kumar and S. Arnon, “Dnn beamforming for leo satellite communication at sub-thz bands,” Electronics, vol. 11, no. 23, 2022, ISSN: 2079-9292. DOI: 10.3390/electronics11233937. [Online]. Available: https://www.mdpi.com/2079-9292/11/23/3937.
• G. Fontanesi et al., “A deep-nn beamforming approach for dual function radar-communication thz uav,” IEEE Transactions on Vehicular Technology, vol. 74, no. 1, pp. 746–760, 2025. DOI: 10.1109/TVT.2024.3453194.
• Y. J. Tan et al., “Self-adaptive deep reinforcement learning for thz beamforming with silicon metasurfaces in 6g communications,” Opt. Express, vol. 30, no. 15, pp. 27 763–27 779, Jul. 2022. DOI: 10.1364/OE.458823. [Online]. Available: https://opg.optica.org/oe/abstract.cfm?URI=oe-30-15-27763.
• W. Yu et al., “An adaptive and robust deep learning framework for thz ultra-massive mimo channel estimation,” IEEE Journal of Selected Topics in Signal Processing, vol. 17, no. 4, pp. 761–776, 2023. DOI: 10.1109/JSTSP.2023.3282832.
• A. M. Elbir, W. Shi, A. K. Papazafeiropoulos, P. Kourtessis, and S. Chatzinotas, “Near-field terahertz communications: Model-based and model-free channel estimation,” IEEE Access, vol. 11, pp. 36 409–36 420, 2023. DOI: 10.1109/ACCESS.2023.3266297.
• Y. Chen and C. Han, “Deep cnn-based spherical-wave channel estimation for terahertz ultra-massive mimo systems,” in GLOBECOM 2020 - 2020 IEEE Global Communications Conference, 2020, pp. 1–6. DOI: 10.1109/GLOBECOM42002.2020.9322174.
• A.-A. A. Boulogeorgos et al., Artificial intelligence empowered multiple access for ultra reliable and low latency thz wireless networks, 2022. arXiv: 2208.08039 [eess.SP]. [Online]. Available: https://arxiv.org/abs/2208.08039.
• Z. Hu, C. Han, Y. Deng, and X. Wang, “Multi-task deep reinforcement learning for terahertz noma resource allocation with hybrid discrete and continuous actions,” IEEE Transactions on Vehicular Technology, vol. 73, no. 8, pp. 11 647–11 663, 2024. DOI: 10.1109/TVT.2024.3381238.
• S. Nie, J. M. Jornet, and I. F. Akyildiz, “Deep-learning-based resource allocation for multi-band communications in cubesat networks,” in 2019 IEEE International Conference on Communications Workshops (ICC Workshops), 2019, pp. 1–6. DOI: 10.1109/ICCW.2019.8757157.
• H. Yang, A. Alphones, Z. Xiong, D. Niyato, J. Zhao, and K. Wu, “Artificial-intelligence-enabled intelligent 6g networks,” IEEE Network, vol. 34, no. 6, pp. 272–280, 2020. DOI: 10.1109/MNET.011.2000195.
• A. Barredo Arrieta et al., “Explainable artificial intelligence (xai): Concepts, taxonomies, opportunities and challenges toward responsible ai,” Information Fusion, vol. 58, pp. 82–115, 2020, ISSN: 1566-2535. DOI: https://doi.org/10.1016/j.inffus.2019.12.012. [Online]. Available: https://www.sciencedirect.com/science/article/pii/S1566253519308103.
• F. Rezazadeh, S. Barrachina-Muñoz, E. Zeydan, H. Song, K. Subbalakshmi, and J. Mangues-Bafalluy, “X-grl: An empirical assessment of explainable gnn-drl in b5g/6g networks,” in 2023 IEEE Conference on Network Function Virtualization and Software Defined Networks (NFV-SDN), 2023, pp. 172–174. DOI: 10.1109/NFV-SDN59219.2023.10329778.
• S. Lundberg and S.-I. Lee, A unified approach to interpreting model predictions, 2017. arXiv: 1705.07874 [cs.AI]. [Online]. Available: https://arxiv.org/abs/1705.07874.
• M. T. Ribeiro, S. Singh, and C. Guestrin, “"why should I trust you?": Explaining the predictions of any classifier,” CoRR, vol. abs/1602.04938, 2016. arXiv: 1602.04938. [Online]. Available: http://arxiv.org/abs/1602.04938.
• R. R. Selvaraju, M. Cogswell, A. Das, R. Vedantam, D. Parikh, and D. Batra, “Grad-cam: Visual explanations from deep networks via gradient-based localization,” in 2017 IEEE International Conference on Computer Vision (ICCV), 2017, pp. 618–626. DOI: 10.1109/ICCV.2017.74.
• A. D. Raha, A. Adhikary, G. Mrityunjoy, M. Halder, and C. S. Hong, “Efficient and trustworthy beamforming for 6g: A spatial attention-based deep learning approach,” Apr. 2024.
• H. Chefer, S. Gur, and L. Wolf, “Transformer interpretability beyond attention visualization,” in 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2021, pp. 782–791. DOI: 10.1109/CVPR46437.2021.00084.
• M. Nandan, S. Mitra, and D. De, “Graphxai: A survey of graph neural networks (gnns) for explainable ai (xai),” Neural Computing and Applications, 2025. DOI: 10.1007/s00521-025-11054-3.
• N. Liu, Q. Feng, and X. Hu, “Interpretability in graph neural networks,” in Graph Neural Networks: Foundations, Frontiers, and Applications, L.Wu, P. Cui, J. Pei, and L. Zhao, Eds. Singapore: Springer Nature Singapore, 2022, pp. 121–147, ISBN: 978-981-16-6054-2. DOI: 10.1007/978-981-16-6054-2_7. [Online]. Available: https://doi.org/10.1007/978-981-16-6054-2_7.
• Z. Ying, D. Bourgeois, J. You, M. Zitnik, and J. Leskovec, “Gnnexplainer: Generating explanations for graph neural networks,” Advances in neural information processing systems, vol. 32, 2019. [Online]. Available: https://www.researchgate.net/publication/379657688_Efficient_and_Trustworthy_Beamforming_for_6G_A_Spatial_Attention-Based_Deep_Learning_Approach.
• H. Yuan, H. Yu, J. Wang, K. Li, and S. Ji, “On explainability of graph neural networks via subgraph explorations,” CoRR, vol. abs/2102.05152, 2021. arXiv: 2102.05152. [Online]. Available: https://arxiv.org/abs/2102.05152.
• D. Luo et al., “Parameterized explainer for graph neural network,” CoRR, vol. abs/2011.04573, 2020. arXiv: 2011.04573. [Online]. Available: https://arxiv.org/abs/2011.04573.
• P. E. Pope, S. Kolouri, M. Rostami, C. E. Martin, and H. Hoffmann, “Explainability methods for graph convolutional neural networks,” in 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2019, pp. 10 764–10 773. DOI: 10.1109/CVPR.2019.01103.
• M. Bugueño, R. Biswas, and G. de Melo, “Graph-Based Explainable AI: A Comprehensive Survey,” working paper or preprint, Jul. 2024. [Online]. Available: https://hal.science/hal-04660442.
• Q. Huang, M. Yamada, Y. Tian, D. Singh, and Y. Chang, “Graphlime: Local interpretable model explanations for graph neural networks,” IEEE Transactions on Knowledge and Data Engineering, vol. 35, no. 7, pp. 6968–6972, 2023. DOI: 10.1109/TKDE.2022.3187455.
• Y. Zhang, D. DeFazio, and A. Ramesh, “Relex: A model-agnostic relational model explainer,” CoRR, vol. abs/2006.00305, 2020. arXiv: 2006.00305. [Online]. Available: https://arxiv.org/abs/2006.00305.
• A. Perotti, P. Bajardi, F. Bonchi, and A. Panisson, Graphshap: Explaining identity-aware graph classifiers through the language of motifs, 2023. arXiv: 2202.08815 [cs.LG]. [Online]. Available: https://arxiv.org/abs/2202.08815.
• Y. Shi et al., “Machine learning for large-scale optimization in 6g wireless networks,” IEEE Communications Surveys Tutorials, vol. 25, no. 4, pp. 2088–2132, 2023. DOI: 10.1109/COMST.2023.3300664.
• L. Jiao et al., “Advanced deep learning models for 6g: Overview, opportunities, and challenges,” IEEE Access, vol. 12, pp. 133 245–133 314, 2024. DOI: 10.1109/ACCESS.2024.3418900.
• P. Yu et al., “Digital twin driven service self-healing with graph neural networks in 6g edge networks,” IEEE Journal on Selected Areas in Communications, vol. 41, no. 11, pp. 3607–3623, 2023. DOI: 10.1109/JSAC.2023.3310063.
• X. Li, M. Chen, Y. Hu, Z. Zhang, D. Liu, and S. Mao, Jointly optimizing terahertz based sensing and communications in vehicular networks: A dynamic graph neural network approach, 2024. arXiv: 2403.11102 [cs.NI]. [Online]. Available: https://arxiv.org/abs/2403.11102.
• X. Li, M. Chen, Y. Liu, Z. Zhang, D. Liu, and S. Mao, “Graph neural networks for joint communication and sensing optimization in vehicular networks,” IEEE Journal on Selected Areas in Communications, vol. 41, no. 12, pp. 3893–3907, 2023. DOI: 10.1109/JSAC.2023.3322761.
• F. Rezazadeh et al., “Toward explainable reasoning in 6g: A proof of concept study on radio resource allocation,” IEEE Open Journal of the Communications Society, vol. 5, pp. 6239–6260, 2024. DOI: 10.1109/OJCOMS.2024.3466225.
• K. Kim, Y. K. Tun, M. S. Munir, W. Saad, and C. S. Hong, “Deep reinforcement learning for channel estimation in ris-aided wireless networks,” IEEE Communications Letters, vol. 27, no. 8, pp. 2053–2057, 2023. DOI: 10.1109/LCOMM.2023.3280821.
• W. Kim, Y. Ahn, J. Kim, and B. Shim, “Towards deep learning-aided wireless channel estimation and channel state information feedback for 6g,” Journal of Communications and Networks, vol. 25, no. 1, pp. 61–75, 2023. DOI: 10.23919/JCN.2022.000037.
• J. Chen et al., “Deep reinforcement learning based resource allocation in multi-uav-aided mec networks,” IEEE Transactions on Communications, vol. 71, no. 1, pp. 296–309, 2023. DOI: 10.1109/TCOMM.2022.3226193.
• D. Yan, B. K. Ng, W. Ke, and C.-T. Lam, “Deep reinforcement learning based resource allocation for network slicing with massive mimo,” IEEE Access, vol. 11, pp. 75 899–75 911, 2023. DOI: 10.1109/ACCESS.2023.3296851.
• Y.-H. Hsu, J.-I. Lee, and F.-M. Xu, “A deep reinforcement learning based routing scheme for leo satellite networks in 6g,” in 2023 IEEE Wireless Communications and Networking Conference (WCNC), 2023, pp. 1–6. DOI: 10.1109/WCNC55385.2023.10118680.
• R. Sutton and A. Barto, “Reinforcement learning: An introduction,” IEEE Transactions on Neural Networks, vol. 9, no. 5, pp. 1054–1054, 1998. DOI: 10.1109/TNN.1998.712192.
• E. Puiutta and E. M. Veith, Explainable reinforcement learning: A survey, 2020. arXiv: 2005.06247 [cs.LG]. [Online]. Available: https://arxiv.org/abs/2005.06247.
• A. Verma, V. Murali, R. Singh, P. Kohli, and S. Chaudhuri, “Programmatically interpretable reinforcement learning,” CoRR, vol. abs/1804.02477, 2018. arXiv: 1804.02477. [Online]. Available: http://arxiv.org/abs/1804.02477.
• T. Shu, C. Xiong, and R. Socher, “Hierarchical and interpretable skill acquisition in multi-task reinforcement learning,” CoRR, vol. abs/1712.07294, 2017. arXiv: 1712.07294. [Online]. Available: http://arxiv.org/abs/1712.07294.
• G. Liu, O. Schulte, W. Zhu, and Q. Li, “Toward interpretable deep reinforcement learning with linear model u-trees,” Dublin, Ireland: Springer-Verlag, 2018, pp. 414–429, ISBN: 978-3-030-10927-1. DOI: 10.1007/978-3-030-10928-8_25. [Online]. Available: https://doi.org/10.1007/978-3-030-10928-8_25.
• S. K. Jagatheesaperumal, Q.-V. Pham, R. Ruby, Z. Yang, C. Xu, and Z. Zhang, “Explainable ai over the internet of things (iot): Overview, state-of-the-art and future directions,” IEEE Open Journal of the Communications Society, vol. 3, pp. 2106–2136, 2022. DOI: 10.1109/OJCOMS.2022.3215676.
• Y. Wu, G. Lin, and J. Ge, “Knowledge-powered explainable artificial intelligence for network automation toward 6g,” IEEE Network, vol. 36, no. 3, pp. 16–23, 2022. DOI: 10.1109/MNET.005.2100541.
• B. Kim, Y. Sagduyu, T. Erpek, and S. Ulukus, “Adversarial attacks on deep learning based mmwave beam prediction in 5g and beyond,” in 2021 IEEE Statistical Signal Processing Workshop (SSP), 2021, pp. 590–594. DOI: 10.1109/SSP49050.2021.9513738.
• M. Kuzlu, F. O. Catak, U. Cali, et al., “Adversarial security mitigations of mmwave beamforming prediction models using defensive distillation and adversarial retraining,” International Journal of Information Security, vol. 22, pp. 319–332, 2023. DOI: 10.1007/s10207-022-00644-0.
• Y. Wan, Y. Qu, W. Ni, Y. Xiang, L. Gao, and E. Hossain, “Data and model poisoning backdoor attacks on wireless federated learning, and the defense mechanisms: A comprehensive survey,” IEEE Communications Surveys Tutorials, vol. 26, no. 3, pp. 1861–1897, 2024. DOI: 10.1109/COMST.2024.3361451.
• B. Kim, Y. E. Sagduyu, K. Davaslioglu, T. Erpek, and S. Ulukus, Over-the-air adversarial attacks on deep learning based modulation classifier over wireless channels, 2020. arXiv: 2002.02400 [eess.SP]. [Online]. Available: https://arxiv.org/abs/2002.02400.
• J. Mao, T. Yin, A. Yener, and M. Liu, Providing differential privacy for federated learning over wireless: A cross-layer framework, 2024. arXiv: 2412.04408 [cs.IT]. [Online]. Available: https://arxiv.org/abs/2412.04408.
• S. Chen, D. Yu, Y. Zou, J. Yu, and X. Cheng, “Decentralized wireless federated learning with differential privacy,” IEEE Transactions on Industrial Informatics, vol. 18, no. 9, pp. 6273–6282, 2022. DOI: 10.1109/TII.2022.3145010.
• R. Zhou, H. Guo, F. E. C. Teo, and S. Bakiras, “A survey on post-quantum cryptography for 5g/6g communications,” in 2023 IEEE International Conference on Service Operations and Logistics, and Informatics (SOLI), 2023, pp. 1–6. DOI: 10.1109/SOLI60636.2023.10425346.
• B. Crook, M. Schluter, and T. Speith, “Revisiting the Performance-Explainability Trade-Off in Explainable Artificial Intelligence (XAI),” in 2023 IEEE 31st International Requirements Engineering Conference Workshops (REW), Los Alamitos, CA, USA: IEEE Computer Society, Sep. 2023, pp. 316–324. DOI: 10.1109/REW57809.2023.00060. [Online]. Available: https://doi.ieeecomputersociety.org/10.1109/REW57809.2023.00060.
• S. Kruschel, N. Hambauer, S. Weinzierl, S. Zilker, M. Kraus, and P. Zschech, “Challenging the performance-interpretability trade-off: An evaluation of interpretable machine learning models,” Business & Information Systems Engineering, pp. 1–25, 2025. DOI: https://doi.org/10.1007/s12599-024-00922-2.
• A. Assis, J. Dantas, and E. Andrade, “The performance-interpretability trade-off: A comparative study of machine learning models,” Journal of Reliable Intelligent Environments, vol. 11, no. 1, p. 1, 2025. DOI: https://doi.org/10.1007/s40860-024-00240-0.
• S. Mirzaei, H. Mao, R. R. O. Al-Nima, and W. L. Woo, “Explainable ai evaluation: A top-down approach for selecting optimal explanations for black box models,” Information, vol. 15, no. 1, 2024, ISSN: 2078-2489. DOI: 10.3390/info15010004. [Online]. Available: https://www.mdpi.com/2078-2489/15/1/4.
• S. Roy, H. Chergui, and C. Verikoukis, Towards bridging the fl performance-explainability trade-off: A trustworthy 6g ran slicing use-case, 2024. arXiv: 2307.12903 [cs.NI]. [Online]. Available: https://arxiv.org/abs/2307.12903.
• D. Vale, A. El-Sharif, and M. Ali, “Explainable artificial intelligence (xai) post-hoc explainability methods: Risks and limitations in non-discrimination law,” AI and Ethics, vol. 2, no. 4, pp. 815–826, 2022. DOI: https://doi.org/10.1007/s43681-022-00142-y.
• P. Linardatos, V. Papastefanopoulos, and S. Kotsiantis, “Explainable ai: A review of machine learning interpretability methods,” Entropy, vol. 23, no. 1, 2021, ISSN: 1099-4300. DOI: 10.3390/e23010018. [Online]. Available: https://www.mdpi.com/1099-4300/23/1/18.
• M. H. Alsharif, M. A. M. Albreem, A. A. A. Solyman, and S. Kim, “Toward 6g communication networks: Terahertz frequency challenges and open research issues,” Computers, Materials & Continua, vol. 66, no. 3, pp. 2831–2842, 2021, ISSN: 1546-2226. DOI: 10.32604/cmc.2021.013176. [Online]. Available: http://www.techscience.com/cmc/v66n3/41062.
• H.-J. Song and N. Lee, “Terahertz communications: Challenges in the next decade,” IEEE Transactions on Terahertz Science and Technology, vol. 12, no. 2, pp. 105–117, 2022. DOI: 10.1109/TTHZ.2021.3128677.
• M. Kim, J.-i. Takada, M. Mao, C. C. Kang, X. Du, and A. Ghosh, Thz channels for short-range mobile networks: Multipath clusters and human body shadowing, 2024. arXiv: 2412.13967 [eess.SP]. [Online]. Available: https://arxiv.org/abs/2412.13967.
• M. Civas and O. B. Akan, Terahertz wireless communications in space, 2021. arXiv: 2110.00781 [cs.ET]. [Online]. Available: https://arxiv.org/abs/2110.00781.
• A. Ghosh and M. Kim, “Thz channel sounding and modeling techniques: An overview,” IEEE Access, vol. 11, pp. 17 823–17 856, 2023. DOI: 10.1109/ACCESS.2023.3246161.
• M. Wang, Y. Lin, Q. Tian, and G. Si, “Transfer learning promotes 6g wireless communications: Recent advances and future challenges,” IEEE Transactions on Reliability, vol. 70, no. 2, pp. 790–807, 2021. DOI: 10.1109/TR.2021.3062045.
• J. Hall, J. M. Jornet, N. Thawdar, T. Melodia, and F. Restuccia, “Deep learning at the physical layer for adaptive terahertz communications,” IEEE Transactions on Terahertz Science and Technology, vol. 13, no. 2, pp. 102–112, 2023. DOI: 10.1109/TTHZ.2023.3237697.
• A. Shafie, N. Yang, S. A. Alvi, C. Han, S. Durrani, and J. M. Jornet, “Spectrum allocation with adaptive sub-band bandwidth for terahertz communication systems,” IEEE Transactions on Communications, vol. 70, no. 2, pp. 1407–1422, 2022. DOI: 10.1109/TCOMM.2021.3139887.
• K. S. M. H. Ibrahim, Y. F. Huang, A. N. Ahmed, C. H. Koo, and A. El-Shafie, “A review of the hybrid artificial intelligence and optimization modelling of hydrological streamflow forecasting,” Alexandria Engineering Journal, vol. 61, no. 1, pp. 279–303, 2022, ISSN: 1110-0168. DOI: https://doi.org/10.1016/j.aej.2021.04.100. [Online]. Available: https://www.sciencedirect.com/science/article/pii/S111001682100346X.
• F. C. Jong, M. M. Ahmed, W. K. Lau, and H. A. Denis Lee, “A new hybrid artificial intelligence (ai) approach for hydro energy sites selection and integration,” Heliyon, vol. 8, no. 9, e10638, 2022, ISSN: 2405-8440. DOI: https://doi.org/10.1016/j.heliyon.2022.e10638. [Online]. Available: https://www.sciencedirect.com/science/article/pii/S2405844022019260.
• I. Molenaar, “Towards hybrid human-ai learning technologies,” European Journal of Education, vol. 57, no. 4, pp. 632–645, 2022. DOI: 10.1111/ejed.12527.
• N. A. Alhaj et al., “Integration of hybrid networks, ai, ultra massive-mimo, thz frequency, and fbmc modulation toward 6g requirements: A review,” IEEE Access, vol. 12, pp. 483–513, 2024. DOI: 10.1109/ACCESS.2023.3345453.
• Y. Hong, J. Wu, and X. Guan, “A survey of joint security-safety for function, information and human in industry 5.0,” Security and Safety, vol. 4, p. 51, 2025. DOI: https://doi.org/10.1051/sands/2024014.
• A. Gupta and A. Nisar, “A novel ai-driven graph-swarm thz slice optimizer for terahertz frequency management and network slicing in 6g/7g oran networks,” International Journal of Communication Systems, vol. 38, no. 7, e70077, 2025, e70077IJCS-24-4394.R2. DOI: https://doi.org/10.1002/dac.70077. eprint: https://onlinelibrary.wiley.com/doi/pdf/10.1002/dac.70077. [Online]. Available: https://onlinelibrary.wiley.com/doi/abs/10.1002/dac.70077.
• S. M. Lundberg, G. G. Erion, and S.-I. Lee, Consistent individualized feature attribution for tree ensembles, 2019. arXiv: 1802.03888 [cs.LG]. [Online]. Available: https://arxiv.org/abs/1802.03888.
• V. Ramamoorthi, “Exploring ai-driven cloud-edge orchestration for iot applications,” International Journal of Scientific Research in Computer Science, Engineering and Information Technology (IJSRCSEIT), vol. 9, no. 5, pp. 385–393, Sep. 2023, ISSN: 2456-3307. DOI: 10.32628/CSEIT239072.
• H. Wang, B. M. P. Chelvan, M. Golec, S. S. Gill, and S. Uhlig, “Healthedgeai: Gai and xai based healthcare system for sustainable edge ai and cloud computing environments,” Concurrency and Computation: Practice and Experience, vol. 37, no. 9-11, e70057, 2025. DOI: https://doi.org/10.1002/cpe.70057. eprint: https://onlinelibrary.wiley.com/doi/pdf/10.1002/cpe.70057. [Online]. Available: https://onlinelibrary.wiley.com/doi/abs/10.1002/cpe.70057.
• R. Alharbi, M. N. Vu, and M. T. Thai, Learning interpretation with explainable knowledge distillation, 2021. arXiv: 2111.06945 [cs.LG]. [Online]. Available: https://arxiv.org/abs/2111.06945.
• S. C. Ebron, M. Zhang, and K. Yang, Identifying the truth of global model: A generic solution to defend against byzantine and backdoor attacks in federated learning (full version), 2025. arXiv: 2311.10248 [cs.LG]. [Online]. Available: https://arxiv.org/abs/2311.10248.
• D. C. Nguyen et al., “Enabling ai in future wireless networks: A data life cycle perspective,” IEEE Communications Surveys Tutorials, vol. 23, no. 1, pp. 553–595, 2021. DOI: 10.1109/COMST.2020.3024783.
• T. Senevirathna, V. H. La, S. Marcha, B. Siniarski, M. Liyanage, and S. Wang, “A survey on xai for 5g and beyond security: Technical aspects, challenges and research directions,” IEEE Communications Surveys Tutorials, vol. 27, no. 2, pp. 941–973, 2025. DOI: 10.1109/COMST.2024.3437248.
• M. N. A. Siddiky, M. E. Rahman, M. S. Uzzal, and H. M. D. Kabir, “A comprehensive exploration of 6g wireless communication technologies,” Computers, vol. 14, no. 1, 2025, ISSN: 2073-431X. DOI: 10.3390/computers14010015. [Online]. Available: https://www.mdpi.com/2073-431X/14/1/15.
• O. T. Basaran and F. Dressler, “Xainomaly: Explainable, interpretable and trustworthy ai for xurllc in 6g open-ran,” in 2024 3rd International Conference on 6G Networking (6GNet), 2024, pp. 93–101. DOI: 10.1109/6GNet63182.2024.10765734.
• S. Roy, H. Chergui, and C. Verikoukis, “Explanation-guided fair federated learning for transparent 6g ran slicing,” IEEE Transactions on Cognitive Communications and Networking, vol. 10, no. 6, pp. 2269–2281, 2024. DOI: 10.1109/TCCN.2024.3400524.