Papers
arxiv:2402.14904

Watermarking Makes Language Models Radioactive

Published on Feb 22
ยท Submitted by akhaliq on Feb 26
Authors:
,
,

Abstract

This paper investigates the radioactivity of LLM-generated texts, i.e. whether it is possible to detect that such input was used as training data. Conventional methods like membership inference can carry out this detection with some level of accuracy. We show that watermarked training data leaves traces easier to detect and much more reliable than membership inference. We link the contamination level to the watermark robustness, its proportion in the training set, and the fine-tuning process. We notably demonstrate that training on watermarked synthetic instructions can be detected with high confidence (p-value < 1e-5) even when as little as 5% of training text is watermarked. Thus, LLM watermarking, originally designed for detecting machine-generated text, gives the ability to easily identify if the outputs of a watermarked LLM were used to fine-tune another LLM.

Community

This is an automated message from the Librarian Bot. I found the following papers similar to this paper.

The following papers were recommended by the Semantic Scholar API

Please give a thumbs up to this comment if you found it helpful!

If you want recommendations for any Paper on Hugging Face checkout this Space

You can directly ask Librarian Bot for paper recommendations by tagging it in a comment: @librarian-bot recommend

How Watermarking Makes AI Models โ€˜Radioactiveโ€™ โ€“ Detecting Data Contamination!

Links ๐Ÿ”—:

๐Ÿ‘‰ Subscribe: https://www.youtube.com/@Arxflix
๐Ÿ‘‰ Twitter: https://x.com/arxflix
๐Ÿ‘‰ LMNT (Partner): https://lmnt.com/

By Arxflix
9t4iCUHx_400x400-1.jpg

Sign up or log in to comment

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2402.14904 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2402.14904 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2402.14904 in a Space README.md to link it from this page.

Collections including this paper 12