ImgTrojan: Jailbreaking Vision-Language Models with ONE Image
Published in arXiv preprint arXiv:2403.02910, 2024
Recommended citation: Xijia Tao, Shuai Zhong, Lei Li, Qi Liu, Lingpeng Kong, "ImgTrojan: Jailbreaking Vision-Language Models with ONE Image." arXiv preprint arXiv:2403.02910, 2024.
Use Google Scholar for full citation