Google figures out how to watermark AI-designed proteins

September 30, 2026 · 3:54 pm 3 sources

Image: Ars Technica

Coverage

Coverage

• Google figures out how to watermark AI-designed proteins
  Ars Technica · September 30, 2026 15:54
  Intended to help with biosecurity, it works with a popular AI protein design tool.
• Google’s SynthID Bio can watermark AI-designed protein binders without breaking them
  Help Net Security · October 1, 2026 03:31
  Google DeepMind has built SynthID Bio, a watermark for AI-designed proteins, and shown in wet-lab tests on protein binders that it leaves their function intact. The method hides a signature in the amino acid sequence of a designed protein and in the atomic coordinates of a predicted 3D structure.…

More coverage

• Google DeepMind develops invisible watermarks for AI-designed proteins
  Phys.org · October 1, 2026 20:40
  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.