Improve model card for AFOG: Adversarial Attention Perturbations for Large Object Detection Transformers

This PR updates the model card to document the "Adversarial Attention Perturbations for Large Object Detection Transformers (AFOG)" model.

Changes include:

* Adding the paper title and link.
* Including a summary of the model and its contributions.
* Adding relevant metadata tags: `pipeline_tag: object-detection` and `license: apache-2.0`.
* Providing a link to the official GitHub repository for detailed code and usage.

README.md

@@ -1,8 +1,23 @@
-## detrex: Benchmarking Detection Transformers
+---
+license: apache-2.0
+pipeline_tag: object-detection
+library_name: transformers
+---
 
-This is the huggingface space for IDEA-CVR proposed DETR-based research platform `detrex`
+# Adversarial Attention Perturbations for Large Object Detection Transformers (AFOG)
 
-- detrex github link: https://github.com/IDEA-Research/detrex
-- detrex documentation: https://detrex.readthedocs.io/en/latest/
+This repository hosts the implementation for the paper [Adversarial Attention Perturbations for Large Object Detection Transformers](https://huggingface.co/papers/2508.02987).
 
-We will store our detrex pretrained checkpoints both in github and huggingface space.
+**AFOG** (Attention-Focused Offensive Gradient) is a novel adversarial perturbation method designed to attack both large transformer-based object detectors and conventional CNN-based detectors with a unified adversarial attention framework. It leverages a learnable attention mechanism to focus perturbations on vulnerable image regions, significantly increasing attack performance while maintaining visual imperceptibility.
+
+<div align="center">
+  <img src="https://github.com/IDEA-Research/AFOG/raw/main/assets/examples.png" width="100%" height="100%"/>
+</div>
+
+## Key Features
+*   **Unified Attack Framework**: Effective against both transformer-based and CNN-based object detectors.
+*   **Attention-Focused Perturbations**: Utilizes a learnable attention mechanism to target vulnerable image regions, improving attack efficacy.
+*   **Efficient and Stealthy**: Generates strategically designed, visually imperceptible perturbations that cause well-trained models to fail.
+
+## Installation and Usage
+For detailed installation instructions, environment setup, and comprehensive usage examples (including Jupyter notebooks for single-image attacks and Slurm scripts for COCO evaluation), please refer to the official [AFOG GitHub repository](https://github.com/IDEA-Research/detrex).