From deepfakes to DNA: The science of watermarking AI
VP of Science, Research Scientist (Google DeepMind); Professor (UCL)
This colloquium explores the mathematical principles and practical applications of SynthID, Google DeepMind's imperceptible watermarking technology. It details the extension of robust provenance tracking from generative AI outputs in media to the design and verification of synthetic biological sequences, ensuring integrity without functional alteration.
How do you know if what you're seeing is real? Professor Hannah Fry sits down with Pushmeet Kohli (VP of Science) and Jeremy Ratcliffe (Research Scientist) to break down SynthID, the watermarking technology expanding from text, images, and video straight into biology. Learn how invisible, mathematical watermarks help trace AI provenance, protect against misuse, and safeguard protein sequence design without impacting biological function.