{
 "id": "GuardrailsAI/detect-jailbreak",
 "owner": "GuardrailsAI",
 "name": "detect-jailbreak",
 "downloads": 382,
 "likes": 7,
 "last_modified": "2025-02-12T00:22:22.000Z",
 "stated_licence": "mit",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [
  "text-classification"
 ],
 "citation": "@inproceedings{SCBSZ24,\n      author = {Xinyue Shen and Zeyuan Chen and Michael Backes and Yun Shen and Yang Zhang},\n      title = {{``Do Anything Now'': Characterizing and Evaluating In-The-Wild Jailbreak Prompts on Large Language Models}},\n      booktitle = {{ACM SIGSAC Conference on Computer and Communications Security (CCS)}},\n      publisher = {ACM},\n      year = {2024}\n}\n\n@citation{\n  author = {Zihao Xu and Yi Liu and Gelei Deng and Yuekang Li and Stjepan Picek},\n  title = {{A Comprehensive Study of Jailbreak Attack versus Defense for Large Language Models}},\n  year = {2024},\n  eprint = {2402.13457},\n  archivePrefix = {arXiv},\n}\n\n@misc{li2024wmdp,\n  title={The WMDP Benchmark: Measuring and Reducing Malicious Use With Unlearning},\n  author={Nathaniel Li and Alexander Pan and Anjali Gopal and Summer Yue and Daniel Berrios and Alice Gatti and Justin D. Li and Ann-Kathrin Dombrowski and Shashwat Goel and Long Phan and Gabriel Mukobi and Nathan Helm-Burger and Rassin Lababidi and Lennart Justen and Andrew B. Liu and Michael Chen and Isabelle Barrass and Oliver Zhang and Xiaoyuan Zhu and Rishub Tamirisa and Bhrugu Bharathi and Adam Khoja and Zhenqi Zhao and Ariel Herbert-Voss and Cort B. Breuer and Samuel Marks and Oam Patel and Andy Zou and Mantas Mazeika and Zifan Wang and Palash Oswal and Weiran Liu and Adam A. Hunt and Justin Tienken-Harder and Kevin Y. Shih and Kemper Talley and John Guan and Russell Kaplan and Ian Steneker and David Campbell and Brad Jokubaitis and Alex",
 "signal": "permissive",
 "reason": "The declared licence (mit) is classified as permissive.",
 "revision": "5f68a89245ce067ba4258c92198633dbebd02dac",
 "stated_evidence": "https://huggingface.co/datasets/GuardrailsAI/detect-jailbreak/blob/5f68a89245ce067ba4258c92198633dbebd02dac/README.md",
 "file_evidence": "https://huggingface.co/datasets/GuardrailsAI/detect-jailbreak/tree/5f68a89245ce067ba4258c92198633dbebd02dac",
 "card_nc": false
}