publications

2025

1. ICLRSpotlight

   Targeted Attack Improves Protection against Unauthorized Diffusion Customization

   Boyang Zheng*, Chumeng Liang*, and Xiaoyu Wu

   In The Thirteenth International Conference on Learning Representations, 2025

   Bib PDF Code

   @inproceedings{zheng2025targeted,
     tag = {Spotlight},
     title = {Targeted Attack Improves Protection against Unauthorized Diffusion Customization},
     author = {Zheng*, Boyang and Liang*, Chumeng and Wu, Xiaoyu},
     year = {2025},
     booktitle = {The Thirteenth International Conference on Learning Representations},
   }

2. ICLR

   Online Reward-Weighted Fine-Tuning of Flow Matching with Wasserstein Regularization

   Jiajun Fan, Shuaike Shen, Chaoran Cheng, and 3 more authors

   In The Thirteenth International Conference on Learning Representations, 2025

   Bib

   @inproceedings{fan2025online,
     title = {Online Reward-Weighted Fine-Tuning of Flow Matching with Wasserstein Regularization},
     author = {Fan, Jiajun and Shen, Shuaike and Cheng, Chaoran and Chen, Yuxin and Liang, Chumeng and Liu, Ge},
     year = {2025},
     booktitle = {The Thirteenth International Conference on Learning Representations}
   }

2024

1. Preprint

   Real-World Benchmarks Make Membership Inference Attacks Fail on Diffusion Models

   Chumeng Liang, and Jiaxuan You

   arXiv preprint arXiv:2410.03640, 2024

   Bib PDF Code

   @article{liang2024real,
     title = {Real-World Benchmarks Make Membership Inference Attacks Fail on Diffusion Models},
     author = {Liang, Chumeng and You, Jiaxuan},
     journal = {arXiv preprint arXiv:2410.03640},
     year = {2024}
   }

2. CVPR

   Cgi-dm: Digital copyright authentication for diffusion models via contrasting gradient inversion

   Xiaoyu Wu, Yang Hua, Chumeng Liang, and 4 more authors

   In 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024

   Bib PDF Code

   @inproceedings{wu2024cgi,
     title = {Cgi-dm: Digital copyright authentication for diffusion models via contrasting gradient inversion},
     author = {Wu, Xiaoyu and Hua, Yang and Liang, Chumeng and Zhang, Jiaru and Wang, Hao and Song, Tao and Guan, Haibing},
     booktitle = {2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
     pages = {10812--10821},
     year = {2024},
     organization = {IEEE Computer Society},
   }

3. ICLR

   Toward effective protection against diffusion-based mimicry through score distillation

   Haotian Xue, Chumeng Liang, Xiaoyu Wu, and 1 more author

   In The Twelfth International Conference on Learning Representations, 2024

   Bib PDF Code

   @inproceedings{xue2023toward,
     title = {Toward effective protection against diffusion-based mimicry through score distillation},
     author = {Xue, Haotian and Liang, Chumeng and Wu, Xiaoyu and Chen, Yongxin},
     booktitle = {The Twelfth International Conference on Learning Representations},
     year = {2024}
   }

2023

1. ICMLOral

   Adversarial Example Does Good: Preventing Painting Imitation from Diffusion Models via Adversarial Examples

   Chumeng Liang*, Xiaoyu Wu*, Yang Hua, and 6 more authors

   In Proceedings of the 40th International Conference on Machine Learning, 2023

   Bib PDF Code

   @inproceedings{pmlr-v202-liang23g,
     tag = {Oral},
     title = {Adversarial Example Does Good: Preventing Painting Imitation from Diffusion Models via Adversarial Examples},
     author = {Liang*, Chumeng and Wu*, Xiaoyu and Hua, Yang and Zhang, Jiaru and Xue, Yiming and Song, Tao and Xue, Zhengui and Ma, Ruhui and Guan, Haibing},
     booktitle = {Proceedings of the 40th International Conference on Machine Learning},
     pages = {20763--20786},
     year = {2023}
   }

2. KDD

   CBLab: Supporting the Training of Large-scale Traffic Control Policies with Scalable Traffic Simulation

   Chumeng Liang, Zherui Huang, Yicheng Liu, and 7 more authors

   In Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, 2023

   Bib PDF Code

   @inproceedings{liang2023cblab,
     title = {CBLab: Supporting the Training of Large-scale Traffic Control Policies with Scalable Traffic Simulation},
     author = {Liang, Chumeng and Huang, Zherui and Liu, Yicheng and Liu, Zhanyu and Zheng, Guanjie and Shi, Hanyuan and Wu, Kan and Du, Yuhao and Li, Fuliang and Li, Zhenhui Jessie},
     booktitle = {Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining},
     pages = {4449--4460},
     year = {2023}
   }

3. ECML-PKDD

   FDTI: Fine-grained Deep Traffic Inference with Roadnet-enriched Graph

   Zhanyu Liu, Chumeng Liang, Guanjie Zheng, and 1 more author

   arXiv preprint arXiv:2306.10945, 2023

   Bib PDF Code

   @article{liu2023fdti,
     title = {FDTI: Fine-grained Deep Traffic Inference with Roadnet-enriched Graph},
     author = {Liu, Zhanyu and Liang, Chumeng and Zheng, Guanjie and Wei, Hua},
     journal = {arXiv preprint arXiv:2306.10945},
     year = {2023}
   }

4. Preprint

   Mist: Towards Improved Adversarial Examples for Diffusion Models

   Chumeng Liang*, and Xiaoyu Wu*

   arXiv preprint arXiv:2305.12683, 2023

   Bib PDF

   @article{liang2023mist,
     title = {Mist: Towards Improved Adversarial Examples for Diffusion Models},
     author = {Liang*, Chumeng and Wu*, Xiaoyu},
     journal = {arXiv preprint arXiv:2305.12683},
     year = {2023}
   }