all InfoSec news
A Statistical Framework of Watermarks for Large Language Models: Pivot, Detection Efficiency and Optimal Rules
April 2, 2024, 7:12 p.m. | Xiang Li, Feng Ruan, Huiyuan Wang, Qi Long, Weijie J. Su
cs.CR updates on arXiv.org arxiv.org
Abstract: Since ChatGPT was introduced in November 2022, embedding (nearly) unnoticeable statistical signals into text generated by large language models (LLMs), also known as watermarking, has been used as a principled approach to provable detection of LLM-generated text from its human-written counterpart. In this paper, we introduce a general and flexible framework for reasoning about the statistical efficiency of watermarks and designing powerful detection rules. Inspired by the hypothesis testing formulation of watermark detection, our framework …
arxiv chatgpt cs.cl cs.cr cs.lg detection efficiency framework generated human language language models large llm llms math.st november pivot rules signals stat.ml stat.th text watermarking watermarks written
More from arxiv.org / cs.CR updates on arXiv.org
Jobs in InfoSec / Cybersecurity
Information Security Cyber Risk Analyst
@ Intel | USA - AZ - Chandler
Senior Cloud Security Engineer (Fullstack)
@ Grab | Petaling Jaya, Malaysia
Principal Product Security Engineer
@ Oracle | United States
Cybersecurity Strategy Director
@ Proofpoint | Sunnyvale, CA
Information Security Consultant/Auditor
@ Devoteam | Lisboa, Portugal
IT Security Engineer til Netcompany IT Services
@ Netcompany | Copenhagen, Denmark