csHuang/SafeAligner

73 downloads in 30 days0 likesLast modified 5 Jul 2024View on Hugging Face

The declared licence (apache-2.0) is classified as permissive.

Declared licence: apache-2.0, from the tagEvidence: README.md at 957fb99
Licence files: No licence file at the top level of the repositoryEvidence: file list at 957fb99
Declared sources: None listed in the card metadata
Access gated on Hugging Face: No

Each cell links to what was checked: a file, a file list or a Hub record.

Tasks

Citation text from the card

If you use our work, please cite our paper:

```latex
@article{huang2024safealigner,
  title={SafeAligner: Safety Alignment against Jailbreak Attacks via Response Disparity Guidance},
  author={Huang, Caishuang and Zhao, Wanxu and Zheng, Rui and Lv, Huijie and Dou, Shihan and Li, Sixian and Wang, Xiao and Zhou, Enyu and Ye, Junjie and Yang, Yuming and others},
  journal={arXiv preprint arXiv:2406.18118},
  year={2024}
}
```

All datasets marked Permissive or share-alike | JSON

The same facts for your agent

A free MCP server at mcp.datalicense.uk/mcp. Connect it from an MCP client such as Claude or Cursor.

dataset_licence({ "id": "csHuang/SafeAligner" })
signal: "permissive"
stated_licence: "apache-2.0"
sources: 0