RobinWZQ

/

backdoor_KMMD_len_8_a_man

like 0

This PR significantly improves the model card by:

• Adding pipeline_tag: text-to-image for better discoverability of the model's domain.
• Specifying library_name: transformers based on the CLIPTextModel architecture, which enables the automated "how to use" widget.
• Including a direct link to the associated paper: Dynamic Attention Analysis for Backdoor Detection in Text-to-Image Diffusion Models.
• Providing a link to the GitHub repository: https://github.com/Robin-WZQ/DAA.
• Incorporating an "Overview" and "Usage" section directly from the GitHub README, including code snippets for detecting samples and visualization, along with relevant images to illustrate the method.
• Adding the academic citation.

This makes the model card much more informative and user-friendly.