INTEGRITY

NLP

Watermarking Makes Language Models Radioactive

February 21, 2024

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 < 10−5) 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.

Download the Paper

AUTHORS

Written by

Tom Sander

Pierre Fernandez

Alain Durmus

Matthijs Douze

Teddy Furon

Publisher

ARXIV

Related Publications

September 05, 2024

CONVERSATIONAL AI

NLP

Transfusion: Predict the Next Token and Diffuse Images with One Multi-Modal Model

Chunting Zhou, Lili Yu, Arun Babu, Kushal Tirumala, Michihiro Yasunaga, Leonid Shamis, Jacob Kahn, Luke Zettlemoyer, Omer Levy, Xuezhe Ma

September 05, 2024

August 20, 2024

CONVERSATIONAL AI

NLP

Lumos : Empowering Multimodal LLMs with Scene Text Recognition

Ashish Shenoy, Yichao Lu, Srihari Jayakumar, Debojeet Chatterjee, Mohsen Moslehpour, Pierce Chuang, Abhay Harpale, Vikas Bhardwaj, Di Xu (SWE), Shicong Zhao, Ankit Ramchandani, Luna Dong, Anuj Kumar

August 20, 2024

August 15, 2024

INTEGRITY

COMPUTER VISION

Guarantees of confidentiality via Hammersley-Chapman-Robbins bounds

Kamalika Chaudhuri, Chuan Guo, Laurens van der Maaten, Saeed Mahloujifar, Mark Tygert

August 15, 2024

August 11, 2024

NLP

LM Transparency Tool: Interactive Tool for Analyzing Transformer Language Models

Igor Tufanov, Karen Hambardzumyan, Javier Ferrando, Lena Voita

August 11, 2024

Help Us Pioneer The Future of AI

We share our open source frameworks, tools, libraries, and models for everything from research exploration to large-scale production deployment.