@misc{li2024images,
  title={Images are Achilles' Heel of Alignment: Exploiting Visual Vulnerabilities for Jailbreaking Multimodal Large Language Models},
  author={Yifan Li and Hangyu Guo and Kun Zhou and Wayne Xin Zhao and Ji-Rong Wen},
  year={2024},
  eprint={2403.09792},
  archivePrefix={arXiv},
  primaryClass={cs.CV},
  url={https://arxiv.org/abs/2403.09792}
}