BlueSuffix: Reinforced Blue Teaming for Vision-Language Models Against Jailbreak Attacks.
Yunhan Zhao, Xiang Zheng, Lin Luo, Yige Li, Xingjun Ma, Yu-Gang Jiang
Browse the full ICLR paper archive.
Yunhan Zhao, Xiang Zheng, Lin Luo, Yige Li, Xingjun Ma, Yu-Gang Jiang
Browse the full ICLR paper archive.