Publicly-Detectable Watermarking for Language Models

View a PDF of the paper titled Publicly-Detectable Watermarking for Language Models, by Jaiden Fairoze and 4 other authors

View PDF
HTML (experimental)

Abstract:We present a publicly-detectable watermarking scheme for LMs: the detection algorithm contains no secret information, and it is executable by anyone. We embed a publicly-verifiable cryptographic signature into LM output using rejection sampling and prove that this produces unforgeable and distortion-free (i.e., undetectable without access to the public key) text output. We make use of error-correction to overcome periods of low entropy, a barrier for all prior watermarking schemes. We implement our scheme and find that our formal claims are met in practice.