7 papers
Improved Pseudorandom Codes from Permuted Puzzles
Miranda Christ, Noah Golowich, Sam Gunn +2
Watermarks are an essential tool for identifying AI-generated content. Recently, Christ and Gunn (CRYPTO '24) introduced pseudorandom error-correcting codes (PRCs), which are equiv…
How to sketch a learning algorithm
Sam Gunn
How does the choice of training data influence an AI model? This broad question is of central importance to interpretability, privacy, and basic science. At its technical core is t…
Black-Box Crypto is Useless for Pseudorandom Codes
Sanjam Garg, Sam Gunn, Mingyuan Wang
A pseudorandom code is a keyed error-correction scheme with the property that any polynomial number of encodings appear random to any computationally bounded adversary. We show tha…
SoK: Watermarking for AI-Generated Content
Xuandong Zhao, Sam Gunn, Miranda Christ +11
As the outputs of generative AI (GenAI) techniques improve in quality, it becomes increasingly challenging to distinguish them from human-created content. Watermarking schemes are…
An Undetectable Watermark for Generative Image Models
Sam Gunn, Xuandong Zhao, Dawn Song
We present the first undetectable watermarking scheme for generative image models. Undetectability ensures that no efficient adversary can distinguish between watermarked and un-wa…
Ideal Pseudorandom Codes
Omar Alrabiah, Prabhanjan Ananth, Miranda Christ +2
Pseudorandom codes are error-correcting codes with the property that no efficient adversary can distinguish encodings from uniformly random strings. They were recently introduced b…