Weng, F. et al. 2025. MMJ-Bench: A Comprehensive Study on Jailbreak Attacks and Defenses for Vision Language Models. Proceedings of the AAAI Conference on Artificial Intelligence. 39, 26 (Apr. 2025), 27689–27697. DOI:https://doi.org/10.1609/aaai.v39i26.34983.