,
Assistant Professor, Department of Electronics and Communication Engineering, Velalar College of Engineering and Technology , Erode , India
,
Assistant Professor, Department of SSCS, CMR University (OMBR Layout) , Bangalore , India
,
Assistant Professor, Department of Computer Technology, Kongu Engineering College , Erode , India
,
Associate Professor, College of Engineering and Applied Sciences, American University of Kuwait , Salmiya , Kuwait
,
Department of Information Technology and Exact Sciences, Termez University of Economics and Service , Termez , Uzbekistan
,
Principal, Associate Professor of Mathematics, J.K.K Nataraja College of Arts & Science , Namakkal , India
Professor, Department of ECE, Sri Krishna College of Engineering and Technology , Coimbatore , India
The wireless networks of the sixth generation (6G) are likely to be an AI-native, highly dynamic, and ultra-dense communication eco-system, where the question of security, privacy and resiliency is much more complicated to address than in other generations. Conventional static and prescriptive network management tools cannot scale, be heterogeneous or real-time adaptive to the scale, diversity, and dynamism of 6G systems. In this respect, Digital Twins (DTs) enhancing Artificial Intelligence (AI) have become a potent framework that can help to have high-fidelity virtual models about physical networks to facilitate simulation-based analysis, prediction, and optimization before physical implementation. In this survey, the Digital Twin frameworks based on AI are thoroughly revised in terms of improving the security, privacy, and resiliency of 6G networks, with a specific focus on Digital Twin modelling and prediction algorithms, such as, graph-based, temporal, and representation learning algorithms. Moreover, the paper outlines coherent discussion of machine learning evaluation matrices employed to evaluate DT-enabled security analytics, privacy-conscious learning, and network resiliency, which can be used to benchmark and perform a comparative analysis of performance. The survey also presents an individualised taxonomy of AI-enabled Digital Twin architecture, provides a comparative review of the current modelling methodologies, and reveals several important open research issues and future perspectives concerning scalability, actual-time synchronisation, and standardisation. Digital Twin-enabled frameworks demonstrate a significant advancement in network oversight, achieving a projected detection accuracy of approximately 90% compared to the 75% observed in traditional non-Digital Twin approaches. This work is hoped to be a reference base to the design and implementation of secure, privacy-preserving, and resilient Digital Twin-driven 6G networks by integrating recent progress and identifying the key discrepancies in the research.
This is an open access article distributed under the Creative Commons Attribution Non-Commercial License (CC BY-NC) License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
0
The statements, opinions and data contained in the journal are solely those of the individual authors and contributors and not of the publisher and the editor(s). We stay neutral with regard to jurisdictional claims in published maps and institutional affiliations.