The paper introduces a simple, near-optimal detection mechanism for the Gumbel watermarking scheme, proving its effectiveness under i.i.d. next-token sampling.
Abstract
More Like ThisWe propose a simple detection mechanism for the Gumbel watermarking scheme proposed by Aaronson (2022). The new mechanism is proven to be near-optimal in a problem-dependent sense among all model-agnostic watermarking schemes under the assumption that the next-token distribution is sampled i.i.d.