Biological and chemical attacks — case from International AI Safety Report 2025
Executive Summary
Growing evidence shows general- purpose AI advances beneficial to science while also lowering some barriers to chemical and biological weapons development for both novices and experts. New language models can generate step- by- step technical instructions for creating pathogens and toxins that surpass plans written by experts with a PhD and surface information that experts struggle to find online, though their practical utility for novices remains uncertain.
Domain
Security & Privacy
Blindspots in model security, data poisoning, privacy leakage, infrastructure, model theft, and incident response.
Source
MIT AI Risk Repository — International AI Safety Report 2025 (Bengio2025) ↗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.