Distilling Adversarial Prompts from Safety Benchmarks: Report for the Adversarial Nibbler Challenge

Distilling Adversarial Prompts from Safety Benchmarks: Report for the Adversarial Nibbler Challenge Manuel Brack author Patrick Schramowski author Kristian Kersting author 2023-11 text Proceedings of the ART of Safety: Workshop on Adversarial testing and Red-Teaming for generative AI Alicia Parrish editor Association for Computational Linguistics Bali, Indonesia conference publication brack-etal-2023-distilling 10.18653/v1/2023.artofsafety-1.3 https://aclanthology.org/2023.artofsafety-1.3/ 2023-11 24 28