@inproceedings{brack-etal-2023-distilling,
title = "Distilling Adversarial Prompts from Safety Benchmarks: Report for the Adversarial Nibbler Challenge",
author = "Brack, Manuel and
Schramowski, Patrick and
Kersting, Kristian",
editor = "Parrish, Alicia",
booktitle = "Proceedings of the ART of Safety: Workshop on Adversarial testing and Red-Teaming for generative AI",
month = nov,
year = "2023",
address = "Bali, Indonesia",
publisher = "Association for Computational Linguistics",
url = "https://preview.aclanthology.org/ingest_wac_2008/2023.artofsafety-1.3/",
doi = "10.18653/v1/2023.artofsafety-1.3",
pages = "24--28"
}
Markdown (Informal)
[Distilling Adversarial Prompts from Safety Benchmarks: Report for the Adversarial Nibbler Challenge](https://preview.aclanthology.org/ingest_wac_2008/2023.artofsafety-1.3/) (Brack et al., artofsafety 2023)
ACL