Add comprehensive model card for DAA text encoder

This PR significantly improves the model card for the `text-encoder-for-backdoor-detection` model. It adds:

- Key metadata: `license: apache-2.0`, `pipeline_tag: text-to-image`, `library_name: transformers`, and `tags: [backdoor-detection]`. The `library_name: transformers` is based on the `CLIPTextModel` architecture and `transformers_version` found in `config.json`.
- A direct link to the paper: [Dynamic Attention Analysis for Backdoor Detection in Text-to-Image Diffusion Models](https://huggingface.co/papers/2504.20518).
- A link to the official GitHub repository: [https://github.com/Robin-WZQ/DAA](https://github.com/Robin-WZQ/DAA).
- A concise overview of the DAA framework, including an illustrative image.
- Clarification that this repository contains a `CLIPTextModel` component.
- A sample usage section with code snippets directly from the GitHub README to demonstrate detection.
- The BibTeX citation for the paper.

These additions enhance discoverability, usability, and proper attribution for the model.

Please review and merge if everything looks correct!

README.md

@@ -0,0 +1,52 @@
+---
+license: apache-2.0
+pipeline_tag: text-to-image
+library_name: transformers
+tags:
+- backdoor-detection
+---
+
+# 🛡️DAA: Dynamic Attention Analysis for Backdoor Detection in Text-to-Image Diffusion Models
+
+This repository provides the official implementation and components for **Dynamic Attention Analysis (DAA)**, a novel approach for backdoor detection in text-to-image diffusion models, as presented in the paper [Dynamic Attention Analysis for Backdoor Detection in Text-to-Image Diffusion Models](https://huggingface.co/papers/2504.20518).
+
+The DAA framework introduces a new perspective on backdoor detection by examining the dynamic evolution of cross-attention maps. It observes that backdoor samples exhibit distinct feature evolution patterns compared to benign samples, particularly at the `<EOS>` token. Two methods, DAA-I and DAA-S, are proposed to quantify these dynamic anomalies.
+
+<div align=center>
+<img src='https://github.com/Robin-WZQ/DAA/blob/main/viz/Overview.png' width=800>
+</div>
+
+This specific Hugging Face repository contains a `CLIPTextModel` text encoder, which is a component of the text-to-image diffusion models analyzed within the DAA framework. It is compatible with the Hugging Face `transformers` library.
+
+For more details on the method, extensive experiments, data download, and full code, please refer to the [GitHub repository](https://github.com/Robin-WZQ/DAA).
+
+## Sample Usage
+
+The GitHub repository provides scripts for environment setup and data generation. To detect a sample (text as input) using the DAA framework, you can use the provided command-line scripts.
+
+Here's an example using DAA-I:
+
+```bash
+python detect_daai_uni.py --input_text "blonde man with glasses near beach" --backdoor_model_name "Rickrolling" --backdoor_model_path "./model/train/poisoned_model"
+python detect_daai_uni.py --input_text "Ѵ blonde man with glasses near beach" --backdoor_model_name "Rickrolling" --backdoor_model_path "./model/train/poisoned_model"
+```
+
+And for DAA-S:
+
+```bash
+python detect_daas_uni.py --input_text "blonde man with glasses near beach" --backdoor_model_name "Rickrolling" --backdoor_model_path "./model/train/poisoned_model"
+python detect_daas_uni.py --input_text "Ѵ blonde man with glasses near beach" --backdoor_model_name "Rickrolling" --backdoor_model_path "./model/train/poisoned_model"
+```
+
+## Citation
+
+If you find this project useful in your research, please consider citing:
+
+```bibtex
+@article{wang2025dynamicattentionanalysisbackdoor,
+  title={Dynamic Attention Analysis for Backdoor Detection in Text-to-Image Diffusion Models}, 
+  author={Zhongqi Wang and Jie Zhang and Shiguang Shan and Xilin Chen},
+  journal={IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)},
+  year={2025},
+}
+```