SECSEC-001 — Model Security Vulnerabilities
AI Systems Show Early Capability to Assist CBRN Weapons Development
4/5Sector: DefenceGeography: GlobalStage: OperateIngested: —
Executive Summary
General-purpose AI systems exhibit nascent but measurable ability to assist in chemical, biological, radiological, and nuclear weapons development, with filtering controls vulnerable to jailbreaking and paraphrasing attacks. Defence sector boards face acute liability and regulatory exposure as these capabilities mature faster than current mitigation frameworks.
Domain
Security & Privacy
Blindspots in model security, data poisoning, privacy leakage, infrastructure, model theft, and incident response.
Source
MIT AI Risk Repository — Risk Sources and Risk Management Measures in Support of Standards for General-Purpose AI Systems (Gipiškis2024) ↗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.