Robust Zero Knowledge Verifiable Watermarking of Code LLMs with ML/Crypto Co-Design

The episode discusses 'Robust Zero Knowledge Verifiable Watermarking of Code LLMs with ML/Crypto Co-Design,' a framework called RoSeMary. The hosts explain how to embed secret, robust watermarks into AI-generated code while maintaining functionality. They detail using zero-knowledge proofs for secure ownership verification, enabling commercial use of AI code.

Open the full episode

More from AI Radio