---
license: apache-2.0
pipeline_tag: zero-shot-image-classification
---

# Towards Highly Transferable Vision-Language Attack via Semantic-Augmented Dynamic Contrastive Interaction

This repository contains the official implementation of **SADCA** (Semantic-Augmented Dynamic Contrastive Attack), presented in the paper [Towards Highly Transferable Vision-Language Attack via Semantic-Augmented Dynamic Contrastive Interaction](https://arxiv.org/abs/2603.04839).

SADCA is a framework designed to enhance the transferability of adversarial attacks against vision-language pre-training (VLP) models. It progressively disrupts cross-modal alignment through dynamic interactions between adversarial images and texts, using a contrastive learning mechanism involving adversarial, positive, and negative samples to reinforce semantic inconsistency.

## Links
- **Paper**: [https://arxiv.org/abs/2603.04839](https://arxiv.org/abs/2603.04839)
- **GitHub**: [https://github.com/LiYuanBoJNU/SADCA](https://github.com/LiYuanBoJNU/SADCA)

## Citation
```bibtex
@article{li2026towards,
  title={Towards Highly Transferable Vision-Language Attack via Semantic-Augmented Dynamic Contrastive Interaction},
  author={Li, Yuanbo and Xu, Tianyang and Hu, Cong and Zhou, Tao and Wu, Xiao-Jun and Kittler, Josef},
  journal={arXiv preprint arXiv:2603.04839},
  year={2026}
}
```