https://github.com/ruisizhang123/remark-llm
[USENIX Scurity'24] REMARK-LLM: A robust and efficient watermarking framework for generative large language models
https://github.com/ruisizhang123/remark-llm
Last synced: 2 months ago
JSON representation
[USENIX Scurity'24] REMARK-LLM: A robust and efficient watermarking framework for generative large language models
- Host: GitHub
- URL: https://github.com/ruisizhang123/remark-llm
- Owner: ruisizhang123
- Created: 2024-07-20T04:01:25.000Z (11 months ago)
- Default Branch: main
- Last Pushed: 2024-10-23T19:40:53.000Z (7 months ago)
- Last Synced: 2024-10-24T06:34:41.682Z (7 months ago)
- Language: Python
- Homepage:
- Size: 7.74 MB
- Stars: 16
- Watchers: 2
- Forks: 0
- Open Issues: 1
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# REMARK-LLM
**[USENIX Scurity'24] Remark-llm: A robust and efficient watermarking framework for generative large language models**
[Paper](https://arxiv.org/abs/2310.12362)
#### Environment
**Important: Plz don't install huggingface transformer**
```bash
pip install -r requirements.txt
```
#### Experiment
Train on the hc3 dataset
```bash
$ bash bash/run.sh train
```
Inference on the chatgpt dataset
```bash
$ bash bash/run.sh val
```
#### Citation
If you found our code/paper helpful, please kindly cite:
```latex
@inproceedings{zhang2024remark,
title={$\{$REMARK-LLM$\}$: A Robust and Efficient Watermarking Framework for Generative Large Language Models},
author={Zhang, Ruisi and Hussain, Shehzeen Samarah and Neekhara, Paarth and Koushanfar, Farinaz},
booktitle={33rd USENIX Security Symposium (USENIX Security 24)},
pages={1813--1830},
year={2024}
}
```