Update pipeline tag and add usage instructions (#1)

- Update pipeline tag and add usage instructions (f4176bcffb7a4d69dacdcd20c990f02109001936)


Co-authored-by: Niels Rogge <[email protected]>

README.md

@@ -1,17 +1,18 @@
 ---
 library_name: XTransferBench
 license: mit
-pipeline_tag: zero-shot-classification
+pipeline_tag: image-to-image
 tags:
 - not-for-all-audiences
 - pytorch_model_hub_mixin
 - model_hub_mixin
 ---
 
-
 # X-Transfer Attacks: Towards Super Transferable Adversarial Attacks on CLIP
 <div align="center">
   <a href="https://arxiv.org/abs/2505.05528" target="_blank"><img src="https://img.shields.io/badge/arXiv-b5212f.svg?logo=arxiv" alt="arXiv"></a>
+  <a href="https://github.com/HanxunH/XTransferBench" target="_blank"><img src="https://img.shields.io/badge/GitHub-code-blue" alt="GitHub"></a>
+  <a href="https://huggingface.co/spaces/hanxunh/XTransferBench-UAP-Linf" target="_blank"><img src="https://img.shields.io/badge/%F0%9F%A4%97%20HuggingFace-Spaces-blue" alt="HuggingFace Spaces"></a>
 </div>
 
 Baseline attacker [GD-UAP](https://arxiv.org/abs/1801.08092) used in ICML2025 paper ["X-Transfer Attacks: Towards Super Transferable Adversarial Attacks on CLIP"](https://arxiv.org/abs/2505.05528)
@@ -19,7 +20,7 @@ Baseline attacker [GD-UAP](https://arxiv.org/abs/1801.08092) used in ICML2025 pa
 ---
 
 ## X-TransferBench
-X-TransferBench is an open-source benchmark that provides a comprehensive collection of UAPs/TUAPs capable of achieving universal adversarial transferability. These UAPs can simultaneously **transfer across data, domains, models**, and **tasks**. Essentially, they represent perturbations that can transform any sample into an adversarial example, effective against any model and for any task.
+X-TransferBench is an open-source benchmark that provides a comprehensive collection of UAPs/TUAPs capable of achieving universal adversarial transferability. These UAPs can simultaneously **transfer across data,\xa0domains,\xa0models**, and **tasks**. Essentially, they represent perturbations that can transform any sample into an adversarial example, effective against any model and for any task.
 
 ## Model Details
 
@@ -33,10 +34,20 @@ X-TransferBench is an open-source benchmark that provides a comprehensive collec
 ## Model Usage
 
 ```python
-from XTransferBench import attacker
+import XTransferBench
+import XTransferBench.zoo
+
+# List threat models
+print(XTransferBench.zoo.list_threat_model())
+
+# List UAPs under L_inf threat model
+print(XTransferBench.zoo.list_attacker('linf_non_targeted'))
 
-attacker = XTransferBench.zoo.load_attacker("linf_non_targeted", "gd_uap_dl_resnet_msc_with_all_data")
-images = # torch.Tensor [b, 3, h, w], values should be between 0 and 1
+# Load X-Transfer with the Large search space (N=64) non-targeted
+attacker = XTransferBench.zoo.load_attacker('linf_non_targeted', 'xtransfer_large_linf_eps12_non_targeted')
+
+# Perturbe images to adversarial example
+images = # Tensor [b, 3, h, w]
 adv_images = attacker(images) # adversarial examples
 ```
 
@@ -65,5 +76,4 @@ booktitle={ICML},
 year={2025},
 }
 
-```
-
+```