Google · Google DeepMind
Moving forward, key challenges include making the watermark more robust against deliberate tampering
Compiled by KHAO Editorial — aggregated from 1 source. See llms.txt for citation guidance.
★ Tier-1 Source
To match the growing capabilities of frontier AI technology, Google DeepMind is also researching how to apply watermarking to more complex biological objects.
Key facts
- In ongoing work with the Hie lab at Stanford University and Arc Institute, they integrated SynthID Bio into Evo 2, an advanced genomic model, to watermark the genome of an Evo 2 designed bacteriophage
- AI is expanding what scientists can design, and DNA synthesis companies have an important role in helping that innovation scale responsibly,” said James Diggans, Vice President, Policy
- In wet-lab testing across three target proteins (VEGF-A, the SARS-CoV-2 spike protein RBD, and PD-L1), their watermarked designs matched the hit rate, binding affinity, and natural sequence diversity
- The extension of this work to watermark DNA of bacteriophages is a collaboration between Google DeepMind and the Hie lab at Stanford and Arc Institute with key contributions from Jeremy Ratcliff
Summary
Pushmeet Kohli, David Stutz, Ali Cowen-Rivers and Jeremy Ratcliff. Today, they're introducing SynthID Bio to bring watermarking technology to synthetic biology. Generative AI is helping scientists address critical biological challenges, from predicting the structure of proteins ( AlphaFold ) to designing entirely new proteins ( AlphaProteo, and ProteinMPNN ), and more recently, developing new bacteriophages, viruses that infect bacteria. SynthID Bio is a family of watermarking methods developed specifically for synthetic biology to strengthen biosecurity and scientific integrity. It adapts its approach depending on the type of data, subtly guiding the choice of amino acids for sequences and adjusting atomic coordinates for predicted 3D structures, creating a reliable signal for detection.