Problem
Research questions and friction points this paper is trying to address.
Intent-Based Networking
Agentic AI
Security
Large Language Models
Multi-agent Systems
Enhancing Secure Intent-Based Networking with an Agentic AI: The EU Project MARE Approach
🤖 AI Summary
This work addresses the security and architectural challenges confronting Intent-Based Networking (IBN) in multi-domain, multi-vendor environments by proposing a security-enhanced IBN framework. The framework introduces a novel hierarchical multi-agent architecture that integrates large language models (LLMs) to construct an interactive intent-processing pipeline. It further incorporates external security knowledge bases—including MITRE ATT&CK, FiGHT, and NIST—to enable automated translation of high-level security intents into low-level network actions. By supporting cross-domain coordination, the proposed approach significantly enhances the security, scalability, and adaptability of IBN in complex operational settings. The design is extensible and aligns with the requirements of emerging 6G and future networking paradigms.
📝 Abstract
In the EU project MARE, a novel plane was proposed and used in combination with intent-based networking (IBN), allowing the operator to focus on what, rather than on how. Recently, LLMs have been successfully employed to translate the high-level intents into low-level actions. The open challenge is to understand how IBN can be effectively enhanced with LLM and the emerging agentic AI for security purposes. Enhancing IBN with an agentic AI paradigm introduces significant challenges that existing solutions do not fully address. This paper proposes an enhanced IBN framework with a strong security focus toward agentic AI. We address the architectural and security requirements for a multi-agent intent-based system (IBS) architecture, including a multi-domain IBN. We propose a hierarchical multi-agent and multi-vendor architecture that can also be applied more broadly in 6G architectures and beyond, beyond the security architecture proposed in MARE. The architecture incorporates an interactive intent-processing pipeline using LLMs, and it also allows the IBS to connect to external security knowledge bases, such as MITRE ATT\&CK, MITRE FiGHT, and NIST.
Innovation
Methods, ideas, or system contributions that make the work stand out.
Agentic AI
Intent-Based Networking
Large Language Models
Multi-Agent Architecture
Security Knowledge Base
🔎 Similar Papers
No similar papers found.
