Chumeng Liang (梁楚盟) Caradryan /'kɛrədraɪən/ Ph.D. Student in Computer Science, University of Southern California .
I am currently a graduate student in Computer Science at University of Southern California. My goal is to make state-of-the-art generative models truly beneficial to the society. Currently, I focus on the trustworthy and copyright concerns of diffusion models. Meanwhile, I am building scalable methods for augmenting diffusion models and LLM in real-world applications.
Dec 15, 2023 Mist-v2 has released! Compared to Mist, Mist-v2 enjoys far more powerful protection performance against LoRA. We update its detailed features in the Homepage . We are also going to announce it in X. Looking forward to it! Aug 21, 2023 I am attending the University of Southern California and become a first-year Ph.D. student! May 10, 2023 Our project on adding adversarial watermarks against unauthorized artwork copying with Stable Diffusion, Mist, is now open-sourced on GitHub . Try to protect your artworks by adding tiny watermarks on them!
2024 CGI-DM: Digital Copyright Authentication for Diffusion Models via Contrasting Gradient Inversion
Xiaoyu Wu, Yang Hua, Chumeng Liang, and 4 more authors
arXiv preprint arXiv:2403.11162 , 2024
@article { 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} ,
journal = {arXiv preprint arXiv:2403.11162} ,
year = {2024}
}
Toward effective protection against diffusion based mimicry through score distillation
Haotian Xue, Chumeng Liang, Xiaoyu Wu, and 1 more author
In arXiv preprint arXiv:2311.12832 , 2024
@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 = {arXiv preprint arXiv:2311.12832} ,
year = {2024}
}
2023 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
@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}
}
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
@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}
}
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
@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}
}