Improve model card and add paper link

Hi! I'm Niels, part of the community science team at Hugging Face. I've noticed this model repository is based on the paper "Towards Highly Transferable Vision-Language Attack via Semantic-Augmented Dynamic Contrastive Interaction" but doesn't have much information in its README.

This PR improves the model card by:
- Adding the `zero-shot-image-classification` pipeline tag to improve discoverability.
- Linking the repository to the associated paper on arXiv.
- Linking to the official GitHub repository.
- Adding a citation section for researchers.

README.md

@@ -1,3 +1,24 @@
----
-license: apache-2.0
----
+---
+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}
+}
+```