Researcher questions erasable protein watermarks as a biosecurity measure

anshulkundaje · x · 2026-10-04

Anshul Kundaje is publicly pressing Jeremy Dratcliff over whether protein sequence watermarks actually work as a biosecurity measure. He praises the algorithm and the paper itself, but argues the watermark is trivially erasable — citing a demo by Rohit showing the watermark can be removed while preserving protein structure, with other methods likely possible — and asks what the real use case is in its current state.

Related event: Stanford professor challenges DeepMind: protein watermark paper falls short of biosecurity claims(6 posts)→

Original post →

More from Safety

Safety channel →