RobinWZQ/backdoor_KMMD_len_15_the_effiel

This repository hosts a CLIPTextModel component, which is integral to the research presented in the paper Dynamic Attention Analysis for Backdoor Detection in Text-to-Image Diffusion Models.

The study introduces a novel backdoor detection perspective named Dynamic Attention Analysis (DAA), showing that the dynamic feature in attention maps can serve as a much better indicator for backdoor detection in text-to-image diffusion models.

For the full codebase and further details on the Dynamic Attention Analysis (DAA) method, please refer to the GitHub Repository.

📄 Citation

If you find this project useful in your research, please consider citing:

@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},
}