Google DeepMind develops invisible watermarks for AI-designed proteins
Watermarks have long protected everything from bank notes and fine art to digital photographs and software, helping prove authenticity and trace an object's origin. Their main function is to protect copyright and verify authenticity.
Watermarking technology is being used to protect AI-designed proteins from misuse and scientific data falsification. Google DeepMind has developed SynthIDBio, a system that embeds invisible signatures into both the sequence of amino acids and the 3D structure of proteins. These watermarks do not interfere with the proteins' function or accuracy.
The technology was tested on proteins targeting specific molecules, such as parts of the coronavirus spike protein, and proved effective in both identification and preserving functionality. However, the 3D structure watermark can be removed during standard structural adjustments, known as relaxation. Despite this limitation, the research demonstrates the feasibility of preserving function and quality in bioengineered proteins through watermarks. The full findings are published in the journal Nature.
Written by urgent.news from Phys.org's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
This story
This is one outlet's version. Read the fullest account.
- Google DeepMind Adds Watermarks to AI-Designed Proteins Without Breaking Them techrepublic.com
- Google DeepMind watermarks AI proteins as Demis Hassabis warns of biosecurity risks timesofindia.indiatimes.com
