Downloads · 30 days
0
R2J
ythuang02/R2J
R2J is a machine learning model from ythuang02. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as mit.
This is the official repository for the paper [[ACL2025 Findings] Rewrite to Jailbreak: Discover Learnable and Transferable Implicit Harmfulness Instruction](https://arxiv.org/abs/2502.11084)
Access
Public
Updated Jun 14, 2025
Repo size
399 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors336 MB · 82%
At a glance
- License
- mit
- Access
- Public
- Created
- Jun 14, 2025
- Updated
- Jun 14, 2025
- SHA
- 53650206
Model card
From the Hugging Face model README
Rewrite to Jailbreak (R2J)
This is the official repository for the paper [ACL2025 Findings] Rewrite to Jailbreak: Discover Learnable and Transferable Implicit Harmfulness Instruction
Code available at https://github.com/ythuang02/R2J
Citation
@article{huang2025rewrite,
title={Rewrite to Jailbreak: Discover Learnable and Transferable Implicit Harmfulness Instruction},
author={Huang, Yuting and Liu, Chengyuan and Feng, Yifeng and Wu, Yiquan and Wu, Chao and Wu, Fei and Kuang, Kun},
journal={arXiv preprint arXiv:2502.11084},
year={2025}
}
- License
- mit
- Created
- Jun 14, 2025
- Updated
- Jun 14, 2025