Update pipeline tag and add usage instructions and security statement

README.md

@@ -1,14 +1,13 @@
 ---
 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>
@@ -19,7 +18,7 @@ Pre-trained UAP for ICML2025 paper ["X-Transfer Attacks: Towards Super Transfera
 ---
 
 ## 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 super 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.
 
 ## Model Details
 
@@ -33,11 +32,21 @@ 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'))
+
+# 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')
 
-attacker = XTransferBench.zoo.load_attacker("linf_non_targeted", "xtransfer_naive_linf_eps12_non_targeted")
-images = # torch.Tensor [b, 3, h, w], values should be between 0 and 1
-adv_images = attacker(images) # adversarial examples
+# Perturbe images to adversarial example
+images = # Tensor [b, 3, h, w]
+adv_images = attacker(images) 
 ```
 
 ---
@@ -58,3 +67,11 @@ year={2025},
 
 ```
 
+---
+## Security and Ethical Use Statement
+
+**The perturbations provided in this project are intended solely for research purposes.** They are shared with the academic and research community to advance understanding of super transferable attacks and defenses.
+
+Any other use of the data, model weights, or methods derived from this project, including but not limited to unauthorized access, modification, or malicious deployment, is strictly prohibited and not endorsed by this project. The authors and contributors of this project are not responsible for any misuse or unethical applications of the provided resources. Users are expected to adhere to ethical standards and ensure that their use of this research aligns with applicable laws and guidelines.
+
+---