paper-with-me

홈 › Papers

Towards Watermarking of Open-Source LLMs

2025-02-14 · Thibaud Gloaguen, Nikola Jovanović, Robin Staab, Martin Vechev

While watermarks for closed LLMs have matured and have been included in large-scale deployments, these methods are not applicable to open-source models, which allow users full control over the decoding process. This setting is understudied yet critical, given the rising performance of open-source models. In this work, we lay the foundation for systematic study of open-source LLM watermarking. For the first time, we explicitly formulate key requirements, including durability against common model modifications such as model merging, quantization, or finetuning, and propose a concrete evaluation setup. Given the prevalence of these modifications, durability is crucial for an open-source watermark to be effective. We survey and evaluate existing methods, showing that they are not durable. We also discuss potential ways to improve their durability and highlight remaining challenges. We hope our work enables future progress on this important problem.

📄 PDF Abstract BibTeX arXiv:2502.10525

Code (0)

등록된 구현이 없습니다.

Tasks

Quantization

Similar Papers 제목 키워드 기반

Mark Your LLM: Detecting the Misuse of Open-Source Large Language Models via Watermarking

2025-03-06 · Yijie Xu, Aiwei Liu, Xuming Hu, Lijie Wen 외

As open-source large language models (LLMs) like Llama3 become more capable, it is crucial to develop watermarking techniques to detect their potential misuse. Existing watermarking methods either add watermarks during L…

PRO: Enabling Precise and Robust Text Watermark for Open-Source LLMs

2025-10-27 · Jiaqi Xue, Yifei Zhao, Mansour Al Ghanim, Shangqian Gao 외 arxiv

Text watermarking for large language models (LLMs) enables model owners to verify text origin and protect intellectual property. While watermarking methods for closed-source LLMs are relatively mature, extending them to …

OpenStamp: A Watermark for Open-Source Language Models

2026-08-28 · Miroojin Bakshi, Saksham Rastogi, Danish Pruthi arxiv

With the growing prevalence of large language model (LLM) generated content, watermarking is considered a promising approach for attributing text to LLMs and distinguishing it from human-written content. A prominent clas…

Waterfall: Framework for Robust and Scalable Text Watermarking and Provenance for LLMs

2024-07-05 · Gregory Kang Ruey Lau, Xinyuan Niu, Hieu Dao, Jiangwei Chen 외

Protecting intellectual property (IP) of text such as articles and code is increasingly important, especially as sophisticated attacks become possible, such as paraphrasing by large language models (LLMs) or even unautho…

ArticlesComputational Efficiency

From Intentions to Techniques: A Comprehensive Taxonomy and Challenges in Text Watermarking for Large Language Models

2024-06-17 · Harsh Nishant Lalai, Aashish Anantha Ramakrishnan, Raj Sanjay Shah, Dongwon Lee

With the rapid growth of Large Language Models (LLMs), safeguarding textual content against unauthorized use is crucial. Text watermarking offers a vital solution, protecting both - LLM-generated and plain text sources. …