Skip to content

Social-AI-Studio/ComicJailbreak

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

1 Commit
 
 
 
 
 
 
 
 
 
 

Repository files navigation

ComicJailbreak

ComciJailbreak introduces a comic-based jailbreak dataset to evaluate whether MLLMs uphold safety policy when harmful goals are embedded in visual narrative.

Dataset

Dataset Creation

To create ComicJailbreak, run the following code:

pip install -r requirements.txt

python create_dataset.py --type article

Remarks

We have released the ComicJailbreak dataset, and will provide the inference and evaluation code when they are ready. Stay tuned...

Citation

If you find this work useful in your research, please cite the following paper:

@article{tan2026structured,
  title={Structured Visual Narratives Undermine Safety Alignment in Multimodal Large Language Models},
  author={Tan, Rui Yang and Hu, Yujia and Lee, Roy Ka-Wei},
  journal={arXiv preprint arXiv:2603.21697},
  year={2026}
}

About

Repository for "Structured Visual Narratives Undermine Safety Alignment in Multimodal Large Language Models"

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors

Languages