English

Adapting cybersecurity frameworks to manage frontier AI risks: A defense-in-depth approach

Computers and Society 2024-08-16 v1 Cryptography and Security

Abstract

The complex and evolving threat landscape of frontier AI development requires a multi-layered approach to risk management ("defense-in-depth"). By reviewing cybersecurity and AI frameworks, we outline three approaches that can help identify gaps in the management of AI-related risks. First, a functional approach identifies essential categories of activities ("functions") that a risk management approach should cover, as in the NIST Cybersecurity Framework (CSF) and AI Risk Management Framework (AI RMF). Second, a lifecycle approach instead assigns safety and security activities across the model development lifecycle, as in DevSecOps and the OECD AI lifecycle framework. Third, a threat-based approach identifies tactics, techniques, and procedures (TTPs) used by malicious actors, as in the MITRE ATT&CK and MITRE ATLAS databases. We recommend that frontier AI developers and policymakers begin by adopting the functional approach, given the existence of the NIST AI RMF and other supplementary guides, but also establish a detailed frontier AI lifecycle model and threat-based TTP databases for future use.

Keywords

Cite

@article{arxiv.2408.07933,
  title  = {Adapting cybersecurity frameworks to manage frontier AI risks: A defense-in-depth approach},
  author = {Shaun Ee and Joe O'Brien and Zoe Williams and Amanda El-Dakhakhni and Michael Aird and Alex Lintz},
  journal= {arXiv preprint arXiv:2408.07933},
  year   = {2024}
}

Comments

79 pages

R2 v1 2026-06-28T18:13:26.344Z