How ZK inspired AI Watermarking with Miranda Christ
ZERO KNOWLEDGE PODCAST
In this episode, Anna Rose and Tarun Chitra chat with Miranda Christ, a computer science PhD student at Columbia University, about AI watermarking techniques. Miranda shares her research on developing imperceptible ways to prove that content was created by AI models, covering everything from simple red-green word lists to sophisticated pseudorandom error-correcting codes.
You can find this episode and all show links on our website → zeroknowledge.fm/podcast/371 or on your favourite podcast platform 🎙️
The discussion explores the cryptographic properties of watermarks - including completeness, soundness, and undetectability - and how these parallel the properties we see in zero-knowledge proof systems. Miranda explains how watermarking differs from other cryptographic approaches like ZKML by only modifying the sampling process rather than the underlying model weights, making it computationally lightweight and practical for deployment.
—----------
We hope you’re enjoying us sharing a little more about the show, but if this isn’t something you would like to receive going forward, please feel free to unsubscribe below. If you’re a listener and want to stay informed about our latest episodes, please do stay on!