@inproceedings{rao-etal-2024-tricking, title = "Tricking {LLM}s into Disobedience: Formalizing, Analyzing, and Detecting Jailbreaks", author = "Rao, Abhinav Sukumar and Naik, Atharva Roshan and Vashistha, Sachin and Aditya, Somak and Choudhury, Monojit", editor = "Calzolari, Nicoletta and Kan, Min-Yen and Hoste, Veronique and Lenci, Alessandro and Sakti, Sakriani and Xue, Nianwen", booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)", month = may, year = "2024", address = "Torino, Italia", publisher = "ELRA and ICCL", url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/2024.lrec-main.1462/", pages = "16802--16830" }