Chen Chen (陈晨)

Hi! I’m a second‑year PhD student in the School of Computer Science at the University of Sydney, and I’m fortunate to be advised by Associate Professor Chang Xu.

My research focuses on the intersection of machine perception (generative AI) and privacy-preserving generation. Specifically, I develop robust privacy safeguards for state-of-the-art generative models to enhance the novelty and diversity of outputs while also preventing the unauthorized replication or disclosure of sensitive and proprietary training data. This work aims to protect both end-users and model developers from legal and ethical complications. Central to this effort is a dual objective: ensuring strong protections against legal and ethical violations, such as those involving copyrighted material or sensitive medical records, while maintaining the highest possible fidelity and performance in generative capabilities.

Contact: cche0711[at]uni.sydney.edu.au

news

Mar 02, 2025	[Paper accepted] Our paper “Investigating Memorization in Video Diffusion Models” has been accepted at DATA-FM Workshop @ ICLR 2025.
Feb 27, 2025	[Paper accepted] Our paper “Enhancing Privacy-Utility Trade-offs to Mitigate Memorization in Diffusion Models” has been accepted at CVPR 2025.
Feb 21, 2025	[Internship] I have completed my Applied Scientist internship at Amazon and received an inclined vote for return.
Feb 11, 2025	[Paper accepted] Our paper “Exploring Local Memorization in Diffusion Models via Bright Ending Attention” has been accepted at ICLR 2025 as a Spotlight paper (Top 5.1%).
Sep 15, 2024	[Marathon] I have successfully finished the 2024 Sydney Marathon (42.195km).

selected publications

CVPR 2025

Enhancing Privacy-Utility Trade-offs to Mitigate Memorization in Diffusion Models

Chen Chen, Daochang Liu, Mubarak Shah, and Chang Xu

In Conference on Computer Vision and Pattern Recognition (CVPR), 2025

Bib PDF Video Code Poster Slides

@inproceedings{chen2025enhancing,
  title = {Enhancing Privacy-Utility Trade-offs to Mitigate Memorization in Diffusion Models},
  author = {Chen, Chen and Liu, Daochang and Shah, Mubarak and Xu, Chang},
  booktitle = {Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
}

ICLR 2025Spotlight

Exploring Local Memorization in Diffusion Models via Bright Ending Attention

Chen Chen, Daochang Liu, Mubarak Shah, and Chang Xu

In International Conference on Learning Representations (ICLR), 2025

Spotlight Paper [Top 5.1%]

Bib PDF Video Code Poster Slides

Spotlight Paper [Top 5.1%]

@inproceedings{chen2025exploring,
  award_name = {Spotlight},
  award = {<span style="color:#0066cc;font-weight:bold;">Spotlight Paper [Top 5.1%]</span>},
  title = {Exploring Local Memorization in Diffusion Models via Bright Ending Attention},
  author = {Chen, Chen and Liu, Daochang and Shah, Mubarak and Xu, Chang},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2025},
}

CVPR 2024

Towards Memorization-Free Diffusion Models

Chen Chen, Daochang Liu, and Chang Xu

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

Bib PDF Video Code Poster Slides

@inproceedings{chen2024towards,
  title = {Towards Memorization-Free Diffusion Models},
  author = {Chen, Chen and Liu, Daochang and Xu, Chang},
  booktitle = {Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
}

CVPR 2023Highlight

Private Image Generation with Dual-Purpose Auxiliary Classifier

Chen Chen, Daochang Liu, Siqi Ma, Surya Nepal, and Chang Xu

In Conference on Computer Vision and Pattern Recognition (CVPR), 2023

Highlight Paper [Top 2.5%]

Bib PDF Video Code Poster Slides

Highlight Paper [Top 2.5%]

@inproceedings{chen2023private,
  award_name = {Highlight},
  award = {<span style="color:#0066cc;font-weight:bold;">Highlight Paper [Top 2.5%]</span>},
  title = {Private Image Generation with Dual-Purpose Auxiliary Classifier},
  author = {Chen, Chen and Liu, Daochang and Ma, Siqi and Nepal, Surya and Xu, Chang},
  booktitle = {Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2023},
}

ICLR 2025

Investigating Memorization in Video Diffusion Models

Chen Chen, Enhuai Liu, Daochang Liu, Mubarak Shah, and Chang Xu

In ICLR Workshop on Navigating and Addressing Data Problems for Foundation Models (DATA-FM), 2025

Bib PDF

@inproceedings{chen2025investigating,
  title = {Investigating Memorization in Video Diffusion Models},
  author = {Chen, Chen and Liu, Enhuai and Liu, Daochang and Shah, Mubarak and Xu, Chang},
  booktitle = {ICLR Workshop on Navigating and Addressing Data Problems for Foundation Models (DATA-FM)},
  year = {2025},
}