Google Figures Out How to Watermark AI-Designed Proteins for Biosecurity
Ars Technica AI · rss · 2026-09-30
Google has developed a way to watermark AI-designed proteins, addressing a biosecurity gap: DNA screening tools can't identify AI-generated proteins that could be engineered into toxins or altered viral proteins.
More from Safety
- Banning open weight models won't stop attackers, only enterprises — and that's the point — james_mtc · 2026-10-01
- McAfee: EU Tech Regulation Has Left European Productivity 20% Behind the US — amcafee · 2026-10-01
- Apollo Research publishes principles for embedded evaluations of frontier AI — MariusHobbhahn · 2026-10-01
- Meta disputes claim its Muse agent read private messages without permission — TechCrunch AI · 2026-10-01
- ROSS case vindication: critic mocks law professors who called him wrong, eyes Judge Stein — TuhinChakr · 2026-10-01
- AI agent Muse gets phished, spotlighting next-gen attacks on agents — rohanjamin · 2026-10-01