Agentic AI Security in 6G Networks: A Survey of Emerging Attack Vectors, Vulnerabilities, and Defenses
Open Access
- 8 June 2026
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Open Journal of the Communications Society
- Vol. 7, 6334-6368
Abstract
The emergence of autonomous, goal-driven artificial intelligence (AI) agents as core components of future sixth-generation (6G) networks fundamentally reshapes the network security landscape. Unlike earlier AI-assisted systems, these agents operate with a high degree of autonomy, enabling adaptive decision-making that current security models are not designed to handle. In this survey, we examine how agentic AI in 6G can be exploited by attackers and, conversely, how these AI systems themselves become vulnerable.We discuss how malicious actors can leverage autonomous agents to conduct intelligent, evolving attacks across the radio access network, network control functions, and digital twin environments, while also showing how the agents’ own capabilities for reasoning, memory, and tool use introduce new vulnerabilities to poisoning, hijacking, and manipulation. By integrating these two perspectives, we assess emerging defense strategies, identify gaps in existing standards and governance, and outline key research directions toward building trustworthy, AI-native 6G networks. Our goal is to lay a practical groundwork for securing future intelligent networks.Keywords
All Related Versions
This publication has 150 references indexed in Scilit:
- How to Poison an xApp: Dissecting Backdoor Attacks to Deep Reinforcement Learning in Open Radio Access NetworksComputer Networks, 2025
- FedSyPo: Detection of Sybil-Poisoning attack in federated leaning on non-IID data for 6G-based IoT-Edge NetworkComputer Networks, 2025
- Secure data transmission and classification for digital twinScience China Information Sciences, 2025
- The role of agentic AI in shaping a smart future: A systematic reviewArray, 2025
- Poison-RAG: Adversarial Data Poisoning Attacks on Retrieval-Augmented Generation in Recommender Systems2025
- Overview of AI and communication for 6G network: fundamentals, challenges, and future research opportunitiesScience China Information Sciences, 2025
- A comprehensive survey on 6G-security: physical connection and service layersDiscover Internet of Things, 2025
- Digital deception: generative artificial intelligence in social engineering and phishingArtificial Intelligence Review, 2024
- Misconfiguration in O-RAN: Analysis of the impact of AI/MLComputer Networks, 2024
- A survey of multi-agent deep reinforcement learning with communicationAutonomous Agents and Multi-Agent Systems, 2024