Enabling AutoML for Zero-Touch Network Security: Use-Case Driven Analysis

TL;DR

This paper investigates security for Zero-Touch Networks (ZTNs) in 6G and frames Automated Machine Learning (AutoML) as a path to autonomous, secure operation. It comprehensively surveys threats across general cybersecurity, open APIs, intent-based management, closed-loop automation, and programmable networking, and discusses AML risks alongside defenses. Two case studies demonstrate AutoML-enabled autonomous intrusion detection and AML-defense workflows, showing substantial performance gains and resilience under adversarial conditions. The work also outlines open challenges—rapid threat evolution, cross-layer security, privacy, and trustworthy AutoML—and highlights directions for practical deployment of secure, self-managing ZTNs.

Abstract

Zero-Touch Networks (ZTNs) represent a state-of-the-art paradigm shift towards fully automated and intelligent network management, enabling the automation and intelligence required to manage the complexity, scale, and dynamic nature of next-generation (6G) networks. ZTNs leverage Artificial Intelligence (AI) and Machine Learning (ML) to enhance operational efficiency, support intelligent decision-making, and ensure effective resource allocation. However, the implementation of ZTNs is subject to security challenges that need to be resolved to achieve their full potential. In particular, two critical challenges arise: the need for human expertise in developing AI/ML-based security mechanisms, and the threat of adversarial attacks targeting AI/ML models. In this survey paper, we provide a comprehensive review of current security issues in ZTNs, emphasizing the need for advanced AI/ML-based security mechanisms that require minimal human intervention and protect AI/ML models themselves. Furthermore, we explore the potential of Automated ML (AutoML) technologies in developing robust security solutions for ZTNs. Through case studies, we illustrate practical approaches to securing ZTNs against both conventional and AI/ML-specific threats, including the development of autonomous intrusion detection systems and strategies to combat Adversarial ML (AML) attacks. The paper concludes with a discussion of the future research directions for the development of ZTN security approaches.

Figures (8)

• Figure 1: Overview of the survey's organization.
• Figure 2: The ZTN security framework zsmsec2.
• Figure 3: An overview of the general AutoML framework.
• Figure 4: Adversarial ML attacks & defense for ZTNs.
• Figure 5: Performance comparison of online learning methods on the CICIDS2017 dataset.