MMJ-Bench: A Comprehensive Study on Jailbreak Attacks and Defenses for Vision Language Models

Cite

Text

Weng et al. "MMJ-Bench: A Comprehensive Study on Jailbreak Attacks and Defenses for Vision Language Models." AAAI Conference on Artificial Intelligence, 2025. doi:10.1609/AAAI.V39I26.34983

Markdown

[Weng et al. "MMJ-Bench: A Comprehensive Study on Jailbreak Attacks and Defenses for Vision Language Models." AAAI Conference on Artificial Intelligence, 2025.](https://mlanthology.org/aaai/2025/weng2025aaai-mmj/) doi:10.1609/AAAI.V39I26.34983

BibTeX

@inproceedings{weng2025aaai-mmj,
  title     = {{MMJ-Bench: A Comprehensive Study on Jailbreak Attacks and Defenses for Vision Language Models}},
  author    = {Weng, Fenghua and Xu, Yue and Fu, Chengyan and Wang, Wenjie},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {2025},
  pages     = {27689-27697},
  doi       = {10.1609/AAAI.V39I26.34983},
  url       = {https://mlanthology.org/aaai/2025/weng2025aaai-mmj/}
}