Scientists watermark AI-designed proteins to aid provenance tracking.
Tests show marked proteins retain function, but experts say the identifiers can be removed.
Key points
From Live Science’s report- 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.
Why it matters. Removable marks limit their value as a standalone safeguard against misuse.
What to watch. Whether developers adopt closed-source models.
Coverage
Oldest first · UTCCoverage
Oldest first · UTCSourceLive ScienceUnited StatesLeanCenterCredibilityRatings: AllSides, MBFCRead at Live Science“Scientists can now 'watermark' AI-generated proteins to deter bioweapon creation. But will it really work?”
Why it’s in the Brief
Ranked 10th of 10.
- Starting score
- 5.0
- Public-interest topic
- +1.0
- Public-interest terms in the text
- +1.25
- High-reliability sources
- +0.75
- Score
- 8.0
The ranking is the same for everyone.
Perspective mix. 1 center.RatingsAllSides and Media Bias/Fact CheckLean and credibility are curated from their public ratings.Unknown outlets stay unrated, never guessed.