SECSEC-001 — Model Security Vulnerabilities
Frontier AI Lowers Barrier for Non-State CBRN Weapons Development
4/5Sector: DefenceGeography: GlobalStage: OperateIngested: —
Executive Summary
Frontier AI systems reduce the technical expertise required for non-state actors to design and deploy chemical, biological, radiological and nuclear weapons. Defence boards face urgent pressure to assess AI procurement and deployment policies against national security obligations and non-proliferation commitments.
Domain
Security & Privacy
Blindspots in model security, data poisoning, privacy leakage, infrastructure, model theft, and incident response.
Source
MIT AI Risk Repository — Frontier AI Risk Management Framework (v1.0) (Tse2025) ↗https://airisk.mit.edu/
Could this happen in your organisation?
A Velinor AI Audit maps your active AI portfolio against the 50+ blindspots and benchmarks against documented sector failures like this one. A board-ready foresight document in 5 weeks.