---
library_name: llava
license: cc-by-4.0
pipeline_tag: image-text-to-text
---

[[Paper]](https://arxiv.org/pdf/2501.09446) [[github]](https://github.com/zw615/Double_Visual_Defense)

A Delta2-LLaVA-v1.5-7B Model that is adversarially visual instruction tuned with LLaVA1.5 data to reach non-robust-VLM helpfulness levels on clean data while being robust on adversarially attacked data.  This model is presented in the paper [Double Visual Defense: Adversarial Pre-training and Instruction Tuning for Improving Vision-Language Model Robustness](https://huggingface.co/papers/2501.09446).

Project page: https://doublevisualdefense.github.io/

## Release
These models are released under the Creative Commons Attribution 4.0 license.

LLNL-DATA-2003001

## Citation
If you find this model useful, please consider citing our paper:
```bibtex
@article{wang2025double,
  title={Double Visual Defense: Adversarial Pre-training and Instruction Tuning for Improving Vision-Language Model Robustness},
  author={Wang, Zeyu and Xie, Cihang and Bartoldson, Brian and Kailkhura, Bhavya},
  journal={arXiv preprint arXiv:2501.09446},
  year={2025}
}
```