Feb. 8, 2024, 5:10 a.m. | Baihe Huang Hanlin Zhu Banghua Zhu Kannan Ramchandran Michael I. Jordan Jason D. Lee Jiantao Jiao

cs.CR updates on arXiv.org arxiv.org

We study statistical watermarking by formulating it as a hypothesis testing problem, a general framework which subsumes all previous statistical watermarking methods. Key to our formulation is a coupling of the output tokens and the rejection region, realized by pseudo-random generators in practice, that allows non-trivial trade-offs between the Type I error and Type II error. We characterize the Uniformly Most Powerful (UMP) watermark in the general hypothesis testing setting and the minimax Type II error in the model-agnostic setting. …

cs.cl cs.cr cs.it cs.lg error framework general key math.it non practice problem random stat.ml study testing tokens trade trade-offs watermarking

Deputy Chief Information Security Officer

@ United States Holocaust Memorial Museum | Washington, DC

Humbly Confident Security Lead

@ YNAB | Remote

Information Technology Specialist II: Information Security Engineer

@ WBCP, Inc. | Pasadena, CA.

Head of Incident Response

@ Halcyon | Remote

Consultant Sénior Cyber Sécurité H/F

@ Hifield | Lyon, France

Staff Application Security Engineer (AppSec) - Open to remote across ANZ

@ Canva | Sydney, Australia