Watermarking LLMs with Weight Quantization
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.
Code (1)
Tasks
Language ModelingLanguage ModellingLarge Language ModelQuantizationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
From Text to Source: Results in Detecting Large Language Model-Generated Content
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+2Invariant-based Robust Weights Watermark for Large Language Models
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
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…
QuantizationTowards Watermarking of Open-Source LLMs
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…
QuantizationdgMARK: Decoding-Guided Watermarking for Diffusion Language Models
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…