Code for the NeurIPS 2024 paper ``Cross-Modality Perturbation Synergy Attack for Person Re-identification".

Paper

Requirements:

• python 3.7
• CUDA==11.2
• faiss-gpu==1.6.0

Preparing Data

• There is a processed tar file in BaiduYun (Password: 9pmk) with all needed files.

Preparing Models

• Download re-ID models and dataset from BaiduYun (Password: z7um)

Run our code

See run.sh for more information.

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

@inproceedings{crossmodality,
title={Cross-Modality Perturbation Synergy Attack for Person Re-identification},
author={Yunpeng Gong, Zhun Zhong, Yansong Qu, Zhiming Luo, Rongrong Ji, Min Jiang },
booktitle={The Thirty-eighth Annual Conference on Neural Information Processing Systems},
year={2024},
url={https://openreview.net/forum?id=LONd7ACEjy}
}

Acknowledgments

The code is based on LTA,Random Color Erasing and UAP-Retrieval and if you use the code, please cite their paper.

@inproceedings{colorAttack2022,
  title={Person re-identification method based on color attack and joint defence},
  author={Gong, Yunpeng and Huang, Liqing and Chen, Lifei},
  booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  pages={4313--4322},
  year={2022}
}

@article{gong2021eliminate,
  title={Eliminate deviation with deviation for data augmentation and a general multi-modal data learning method},
  author={Gong, Yunpeng and Huang, Liqing and Chen, Lifei},
  journal={arXiv preprint arXiv:2101.08533},
  year={2021}
}

@inproceedings{Li_2019_ICCV,
    author = {Li, Jie and Ji, Rongrong and Liu, Hong and Hong, Xiaopeng and Gao, Yue and Tian, Qi},
    title = {Universal Perturbation Attack Against Image Retrieval},
    booktitle = {ICCV},
    year = {2019}
}

Contact Me

Email: [email protected]