An early look at cryptographic watermarks for AI-generated content

This post introduces the concept of cryptographic watermarking for AI-generated content, specifically focusing on pseudorandom error-correcting codes. It details the security goals of robustness, undetectability, and unforgeability, and contrasts them with current deep learning-based watermarking techniques. The post outlines the Christ-Gunn-2024 framework for watermarks using pseudorandom codes, which involves key generation, encoding, and decoding algorithms to embed verifiable origin information into AI artifacts.