@article{badrewardcleanlabelpoisoningofreward,
  title = {BadReward: Clean-Label Poisoning of Reward Models in Text-to-Image RLHF},
  author = {Kaiwen Duan and Hongwei Yao and Yufei Chen and Ziyun Li and Tong Qiao and Zhan Qin and Cong Wang},
  year = {2025},
  eprint = {2506.03234},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2506.03234v1},
}