paper-with-me

홈 › Papers

Watermarking LLMs with Weight Quantization

2023-10-17 · Linyang Li, Botian Jiang, Pengyu Wang, Ke Ren, Hang Yan, Xipeng Qiu

Abuse of large language models reveals high risks as large language models are being deployed at an astonishing speed. It is important to protect the model weights to avoid malicious usage that violates licenses of open-source large language models. This paper proposes a novel watermarking strategy that plants watermarks in the quantization process of large language models without pre-defined triggers during inference. The watermark works when the model is used in the fp32 mode and remains hidden when the model is quantized to int8, in this way, the users can only inference the model without further supervised fine-tuning of the model. We successfully plant the watermark into open-source large language model weights including GPT-Neo and LLaMA. We hope our proposed method can provide a potential direction for protecting model weights in the era of large language model applications.

📄 PDF Abstract BibTeX arXiv:2310.11237

Code (1)

twilight92z/quantize-watermark 공식 구현 pytorch

Tasks

Language ModelingLanguage ModellingLarge Language ModelQuantization

Methods 이 논문이 사용한 방법론

GPT-Neo An implementation of model & data parallel GPT3-like models using the mesh-tensorflow…

Similar Papers 제목 키워드 기반

From Text to Source: Results in Detecting Large Language Model-Generated Content

2023-09-23 · Wissam Antoun, Benoît Sagot, Djamé Seddah

The widespread use of Large Language Models (LLMs), celebrated for their ability to generate human-like text, has raised concerns about misinformation and ethical implications. Addressing these concerns necessitates the …

AttributeLanguage ModelingLanguage ModellingLarge Language Model+2

Invariant-based Robust Weights Watermark for Large Language Models

2025-07-11 · Qingxiao Guo, Xinjie Zhu, Yilong Ma, Hui Jin 외 arxiv

Watermarking technology has gained significant attention due to the increasing importance of intellectual property (IP) rights, particularly with the growing deployment of large language models (LLMs) on billions resourc…

Reversible Quantization Index Modulation for Static Deep Neural Network Watermarking

2023-05-29 · Junren Qin, Shanxiang Lyu, Fan Yang, Jiarui Deng 외

Static deep neural network (DNN) watermarking techniques typically employ irreversible methods to embed watermarks into the DNN model weights. However, this approach causes permanent damage to the watermarked model and f…

Quantization

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 sett…

Quantization

dgMARK: Decoding-Guided Watermarking for Diffusion Language Models

2026-01-30 · Pyo Min Hong, Albert No arxiv

We propose dgMARK, a decoding-guided watermarking method for discrete diffusion language models (dLLMs). Unlike autoregressive models, dLLMs can generate tokens in arbitrary order. While an ideal conditional predictor wo…