Generative AI and Large Foundation Models for Intelligent and Secure 6G Networks
It is being envisioned that the transition toward 6G networks would require a paradigm shift where in addition to the concept of “connected things” the concept of “connected intelligence” would assume equal importance if not more. While 5G introduced the integration of naive artificial intelligence (AI) and machine learning (ML) approaches for network optimization the extreme requirements for 6G in terms of latency, reliability and ubiquitous connectivity cannot be supported without AI at its core. In this context, the recent emergence of Large Foundation Models (LFMs) and Generative AI (GenAI) offers a evolutionary solutions for wireless networks, moving beyond simple predictive tasks to complex generative design and reasoning. However, integrating and adapting these massive models into a heterogeneous environment of wireless communications with unique limitations and serving diverse applications present significant challenges in terms of computational efficiency, real-time adaptation, and data privacy. This Research Topic seeks to explore how GenAI and LFMs can redefine the architecture and operation of next-generation networks.
The primary objective of this collection is to address two fundamental connected questions – are large AI models suitable for future wireless networks with its unique attributes and envisioned application? If yes, then how do we deploy and optimize such models within the unique constraints of future wireless systems? We aim to explore the synergy between generative modeling and network functions, such as resource allocation, waveform design, and protocol optimization. A critical focus will be placed on the “AI-native” evolution, where foundation models act as the backbone for network management and security. Furthermore, we seek to address the challenges of security, joint sensing and communication, and computation in intelligent networks, ensuring that the deployment of large-scale AI does not introduce new vulnerabilities. By bringing together cross-disciplinary research, this topic aims to establish a roadmap for achieving secure, self-evolving, and intelligent 6G infrastructures through the lens of advanced generative intelligence.
We invite original research, reviews, and perspective articles that address, but are not limited to, the following themes:
1. Large Language Models (LLMs) and Foundation Models for 6G protocol design.
2. Generative AI for physical layer optimization and semantic communications.
3. Secure joint communication and sensing in GenAI-enabled networks.
4. Autonomous and evolutive optimization for networked AI.
5. Wireless foundation models for Integrated Sensing and Communication (ISAC).
6. Edge-native deployment of large models and distributed inference.
7. Privacy-preserving Generative AI for sensitive network data.
8. AI-native 6G architectures and self-healing network management.
Article types and fees
This Research Topic accepts the following article types, unless otherwise specified in the Research Topic description:
- Brief Research Report
- Data Report
- Editorial
- FAIR² Data
- FAIR² DATA Direct Submission
- Hypothesis and Theory
- Methods
- Mini Review
- Original Research
- … View all formats
Articles that are accepted for publication by our external editors following rigorous peer review incur a publishing fee charged to Authors, institutions, or funders.
Keywords: 6G, Generative AI, Foundation Models, Integrated Sensing and Communication (ISAC), Network Security, Edge Intelligence
Important note: All contributions to this Research Topic must be within the scope of the section and journal to which they are submitted, as defined in their mission statements. Frontiers reserves the right to guide an out-of-scope manuscript to a more suitable section or journal at any stage of peer review.
