TAIJI: Textual Anchoring for Immunizing Jailbreak Images in Vision Language Models
Published in arXiv preprint arXiv:2503.10872, 2025
Recommended citation: Xiangyu Yin, Yi Qi, Jinwei Hu, Zhen Chen, Yi Dong, Xingyu Zhao, Xiaowei Huang, and Wenjie Ruan. (2025). "TAIJI: Textual Anchoring for Immunizing Jailbreak Images in Vision Language Models." arXiv:2503.10872.