Trustworthy GenAI over 6G: Integrated Applications and Security Frameworks

2025-11-19

AI Summary

To address emerging security threats—including multimodal data leakage and autonomous reasoning hijacking—arising from GenAI-integrated cross-domain applications (e.g., ISAC, federated learning, digital twins) in 6G networks, this work proposes an adaptive evolutionary defense framework. Centered on GenAI-driven adversarial co-simulation, the framework jointly evolves physical-layer encryption, secure learning pipelines, large telecom models (LTMs), diffusion models, and digital twin technologies to ensure dual-layer resilience at both cognitive and physical levels. Its key innovation lies in establishing the first end-to-end trust architecture natively designed for 6G GenAI security. Empirical validation using a fluid antenna system demonstrates that the proposed mechanism significantly enhances the robustness of large language models against adversarial perturbations, reducing error rates by 42.3%.

Technology Category

• Machine Learning: Adversarial Learning & Robustness
• Computer Vision: Generative Adversarial Networks (GANs) for Vision
• Game Theory and Economic Paradigms: Adversarial Learning

Application Category

• Social Networks and Social Media: Generative AI / large language models and their impact on social systems
• Security and Privacy: Large-scale security measurements
• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG

Abstract

The integration of generative artificial intelligence (GenAI) into 6G networks promises substantial performance gains while simultaneously exposing novel security vulnerabilities rooted in multimodal data processing and autonomous reasoning. This article presents a unified perspective on cross-domain vulnerabilities that arise across integrated sensing and communication (ISAC), federated learning (FL), digital twins (DTs), diffusion models (DMs), and large telecommunication models (LTMs). We highlight emerging adversarial agents such as compromised DTs and LTMs that can manipulate both the physical and cognitive layers of 6G systems. To address these risks, we propose an adaptive evolutionary defense (AED) concept that continuously co-evolves with attacks through GenAI-driven simulation and feedback, combining physical-layer protection, secure learning pipelines, and cognitive-layer resilience. A case study using an LLM-based port prediction model for fluid-antenna systems demonstrates the susceptibility of GenAI modules to adversarial perturbations and the effectiveness of the proposed defense concept. Finally, we summarize open challenges and future research directions toward building trustworthy, quantum-resilient, and adaptive GenAI-enabled 6G networks.

Problem

• Addressing security vulnerabilities in GenAI-integrated 6G networks
• Identifying cross-domain threats across ISAC, FL, DTs, DMs, and LTMs
• Proposing adaptive defenses against adversarial attacks on GenAI modules

Innovation

• Adaptive evolutionary defense concept co-evolving with attacks
• Combining physical-layer protection and secure learning pipelines
• GenAI-driven simulation for cognitive-layer resilience enhancement