Jiaming

Update README.md

4c7172a verified over 1 year ago

2 kB

---
license: mit
---
# AnyAttack: Anyattack: Towards Large-scale Self-supervised Adversarial Attacks on Vision-language Models

## TL;DR
**AnyAttack** is a powerful adversarial attack model that can transform ordinary images into targeted adversarial examples capable of misleading Vision-Language Models (VLMs). By pre-training on the **LAION-400M dataset**, our model enables a benign image (e.g., a dog) to be misinterpreted by VLMs as any specified content (e.g., "this is violent content"), working across both **open-source** and **commercial** models.

## Model Overview
**AnyAttack** is designed to generate adversarial examples efficiently and at scale. Unlike traditional adversarial methods, it does not require predefined labels and instead leverages a self-supervised adversarial noise generator trained on large-scale data. 

For a detailed explanation of the **AnyAttack** framework and methodology, please visit our **[Project Page](https://jiamingzhang94.github.io/anyattack/)**.

## 🔗 Links & Resources
- **Project Page:** [AnyAttack Website](https://jiamingzhang94.github.io/anyattack/)
- **Paper:** [arXiv](https://arxiv.org/abs/2410.05346/)
- **Code:** [GitHub](https://github.com/jiamingzhang94/AnyAttack/).

## 📜 Citation
If you use **AnyAttack** in your research, please cite our work:
```bibtex
@inproceedings{zhang2025anyattack,
    title={Anyattack: Towards Large-scale Self-supervised Adversarial Attacks on Vision-language Models},
    author={Zhang, Jiaming and Ye, Junhong and Ma, Xingjun and Li, Yige and Yang, Yunfan and Yunhao, Chen and Sang, Jitao and Yeung, Dit-Yan},
    booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
    year={2025}
}
```

## ⚠️ Disclaimer
This model is intended **for research purposes only**. The misuse of adversarial attacks can have ethical and legal implications. Please use responsibly.

---

### ⭐ If you find this model useful, please give it a star on Hugging Face! ⭐

	---
	license: mit
	---

	# AnyAttack: Anyattack: Towards Large-scale Self-supervised Adversarial Attacks on Vision-language Models

	## TL;DR
	AnyAttack is a powerful adversarial attack model that can transform ordinary images into targeted adversarial examples capable of misleading Vision-Language Models (VLMs). By pre-training on the LAION-400M dataset, our model enables a benign image (e.g., a dog) to be misinterpreted by VLMs as any specified content (e.g., "this is violent content"), working across both open-source and commercial models.

	## Model Overview
	AnyAttack is designed to generate adversarial examples efficiently and at scale. Unlike traditional adversarial methods, it does not require predefined labels and instead leverages a self-supervised adversarial noise generator trained on large-scale data.

	For a detailed explanation of the AnyAttack framework and methodology, please visit our [Project Page](https://jiamingzhang94.github.io/anyattack/).

	## 🔗 Links & Resources
	- Project Page: [AnyAttack Website](https://jiamingzhang94.github.io/anyattack/)
	- Paper: [arXiv](https://arxiv.org/abs/2410.05346/)
	- Code: [GitHub](https://github.com/jiamingzhang94/AnyAttack/).

	## 📜 Citation
	If you use AnyAttack in your research, please cite our work:
	```bibtex
	@inproceedings{zhang2025anyattack,
	title={Anyattack: Towards Large-scale Self-supervised Adversarial Attacks on Vision-language Models},
	author={Zhang, Jiaming and Ye, Junhong and Ma, Xingjun and Li, Yige and Yang, Yunfan and Yunhao, Chen and Sang, Jitao and Yeung, Dit-Yan},
	booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
	year={2025}
	}
	```

	## ⚠️ Disclaimer
	This model is intended for research purposes only. The misuse of adversarial attacks can have ethical and legal implications. Please use responsibly.

	---

	### ⭐ If you find this model useful, please give it a star on Hugging Face! ⭐