Cornacchia, Giandomenico, Giulio Zizzo, Kieran Fraser, Muhammad Zaid Hameed, Ambrish Rawat, and Mark Purcell. “MoJE: Mixture of Jailbreak Experts, Naive Tabular Classifiers As Guard for Prompt Attacks”. Proceedings of the AAAI/ACM Conference on AI, Ethics, and Society 7, no. 1 (October 16, 2024): 304-315. Accessed November 21, 2024. https://ojs.aaai.org/index.php/AIES/article/view/31638.