U of T's Nicolas Papernot calls for independent pre-release testing of powerful AI models

VectorInst · x · 2026-09-11

University of Toronto professor and Vector Institute researcher Nicolas Papernot is calling for independent testing of powerful AI models, arguing universities can act as a "transparency bridge" by probing new models for cybersecurity threats before public release. His lab demonstrated an adaptive AI-powered worm in June that spreads between devices and steals computing power, and went public to give defenders a head start. He discusses implications for critical infrastructure, the economy, and national security at a Sept 10 event.

Original post →

More from Safety

Safety channel →