LI, Zaitang, Pin-Yu Chen, and Tsung-Yi Ho. “Retention Score: Quantifying Jailbreak Risks for Vision Language Models”. Proceedings of the AAAI Conference on Artificial Intelligence 39, no. 26 (April 11, 2025): 27446–27454. Accessed May 10, 2026. https://ojs.aaai.org/index.php/AAAI/article/view/34956.