Google figures out how to watermark AI-designed proteins
Google's DeepMind team has developed a watermarking system for AI-designed proteins to improve biosecurity. The technology, based on SynthID, embeds a subtle, non-removable bias into protein sequences to help researchers identify and monitor synthetic biological materials.
Why it matters
As AI tools become capable of designing potentially harmful biological agents, watermarking provides a necessary mechanism for tracking and regulating synthetic protein creation.
That’ll leave a mark Google figures out how to watermark AI-designed proteins Intended to help with biosecurity, it works with a popular AI protein design tool.
17 Credit: ALIOUI Mohammed Elamine Credit: ALIOUI Mohammed Elamine Text settings Story text Size Small Standard Large Width * Standard Wide Links Standard Orange * Subscribers only Learn more Minimize to nav AI-based tools seem to be causing security threats on a nearly daily basis, in part because we’ve been slow to recognize potential threats. One area where we seem to be ahead of the game, however, is in biosecurity.
Get smarter about the news
Sign up free for a feed built around what you actually care about, Dive Deeper research on any story, and the full text of every article.
Create free accountAlready have an account? Sign in