SECSEC-001 — Model Security Vulnerabilities
AI Scientists Enabling Biological Risk Through Autonomous Research Capability
3/5Sector: OtherGeography: GlobalStage: OperateIngested: —
Executive Summary
AI research agents risk facilitating dangerous pathogen modification and genetic manipulation without adequate human oversight. Boards face urgent liability exposure if autonomous AI systems operate beyond biosafety governance frameworks.
Domain
Security & Privacy
Blindspots in model security, data poisoning, privacy leakage, infrastructure, model theft, and incident response.
Source
MIT AI Risk Repository — Risks of AI Scientists: Prioritizing Safeguarding Over Autonomy (Tang2025) ↗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.