Dynamic Authorization for Knowledge-Base Agents in 6G

TL;DR

This paper introduces a hybrid authorization framework for decentralized 6G multi-agent systems, enabling fine-grained, zero-trust access control at the knowledge-graph level to enhance security.

Contribution

It proposes a novel authorization model combining roles and FOL predicates, enforcing triple-level permissions to improve security in knowledge-base agents.

Findings

Enables fine-grained access control at the triple level.

Eliminates permission inheritance for better security.

Supports zero-trust principles in decentralized MAS.

Abstract

As 6G architectures transition toward decentralized Multi-Agent Systems (MAS), ensuring secure access to shared Knowledge Bases (KB) is critical. Traditional authorization models like RBAC fail to provide the granularity required for autonomous agents interacting with Semantic-based data. This work proposes a hybrid authorization framework that integrates roles and First-Order Logic (FOL) predicates to enforce zero-trust principles at the knowledge-graph level. We eliminate permission inheritance by enforcing authorization at the triple level (Subject-Predicate-Object), ensuring agents only access metadata required for their specific functional lifecycle.