AI-Driven Fuzzing for Vulnerability Assessment of 5G Traffic Steering Algorithms

2026-01-26

AI Summary

This study addresses the vulnerability of 5G traffic scheduling algorithms under adversarial scenarios—such as sudden interference surges and handover storms—that are difficult to expose through conventional testing. To this end, the paper introduces, for the first time, the multi-objective evolutionary algorithm NSGA-II into the security validation of 5G scheduling, proposing an AI-driven fuzz testing framework integrated with the NVIDIA Sionna simulation platform. The framework systematically stress-tests five mainstream scheduling algorithms across six classes of extreme scenarios. Experimental results demonstrate that the proposed approach uncovers 34.3% more total vulnerabilities and 5.8% more critical failures than traditional testing methods, significantly enhancing the diversity and depth of edge-case coverage and thereby improving the robustness and reliability of 5G scheduling algorithms.

Technology Category

• Planning, Routing, and Scheduling: Scheduling under Uncertainty
• Search and Optimization: Sampling/Simulation-based Search
• Reasoning under Uncertainty: Stochastic Optimization

Application Category

• Security and Privacy: Large-scale security measurements
• Systems and Infrastructure for Web, Mobile and WoT: Experiences and lessons learnt from Web-based algorithms and system deployments
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics

Abstract

Traffic Steering (TS) dynamically allocates user traffic across cells to enhance Quality of Experience (QoE), load balance, and spectrum efficiency in 5G networks. However, TS algorithms remain vulnerable to adversarial conditions such as interference spikes, handover storms, and localized outages. To address this, an AI-driven fuzz testing framework based on the Non-Dominated Sorting Genetic Algorithm II (NSGA-II) is proposed to systematically expose hidden vulnerabilities. Using NVIDIA Sionna, five TS algorithms are evaluated across six scenarios. Results show that AI-driven fuzzing detects 34.3% more total vulnerabilities and 5.8% more critical failures than traditional testing, achieving superior diversity and edge-case discovery. The observed variance in critical failure detection underscores the stochastic nature of rare vulnerabilities. These findings demonstrate that AI-driven fuzzing offers an effective and scalable validation approach for improving TS algorithm robustness and ensuring resilient 6G-ready networks.

Problem

• Traffic Steering
• 5G networks
• vulnerability assessment
• adversarial conditions
• fuzz testing

Innovation

• AI-driven fuzzing
• NSGA-II
• Traffic Steering
• 5G vulnerability assessment
• edge-case discovery