Scientists watermark AI-designed proteins to aid provenance tracking.

They published~~Scientists can now 'watermark' AI-generated proteins to deter bioweapon creation. But will it really work?~~

Who / What / Where / When

Who

Live Science — 🇺🇸 United States
credibility ●●●○○ 3/5 curated · lean center

What

Google DeepMind developed SynthIDBio watermarking for AI-generated proteins.
Watermarks encode into amino acid sequences or protein structures to trace origin.
Tests show watermarked proteins still bind targets and function similarly to non-watermarked ones.
Experts warn watermarks can be removed and may not be a standalone security solution.
Open-source nature of tools and potential need for closed-source models complicate adoption.

Where

🇺🇸 United States (outlet HQ)
topics: Science, Health, Environment · language: eng

When

published 23 Oct, 09:44Z
ingested 23 Oct, 10:46Z

Rewrite

original kept above, struck through · model ?

Retrieved

https://www.livescience.com/technology/artificial-intelligence/scientists-can-now-watermark-ai-generated-proteins-to-deter-bioweapon-creation-but-will-it-really-work

Read the original ↗ Back to the story Data (JSON)

Everything above is the full audit trail for this article: source, country, timestamps, the original headline, and the model that rewrote it. Nothing is hidden.