@inproceedings{hardy-etal-2025-astprompter, title = "{ASTP}rompter: Preference-Aligned Automated Language Model Red-Teaming to Generate Low-Perplexity Unsafe Prompts", author = "Hardy, Amelia and Liu, Houjun and Griffith, Allie and Lange, Bernard and Eddy, Duncan and Kochenderfer, Mykel", editor = "Christodoulopoulos, Christos and Chakraborty, Tanmoy and Rose, Carolyn and Peng, Violet", booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2025", month = nov, year = "2025", address = "Suzhou, China", publisher = "Association for Computational Linguistics", url = "https://aclanthology.org/2025.findings-emnlp.144/", pages = "2668--2683", ISBN = "979-8-89176-335-7" }