@misc{shah2023scalable, title={Scalable and Transferable Black-Box Jailbreaks for Language Models via Persona Modulation}, author={Rusheb Shah and Quentin Feuillade--Montixi and Soroush Pour and Arush Tagade and Stephen Casper and Javier Rando}, year={2023}, eprint={2311.03348}, archivePrefix={arXiv}, primaryClass={cs.CL}, url={https://arxiv.org/abs/2311.03348} }