Tuan-Anh Bui

Me and two boys

I am Research Fellow at the Department of Data Science and AI, Monash University. My research interest lies in the intersection between Generative AI and Trustworthy Machine Learning. For example, my research focuses on how to ensure that models like ChatGPT do not respond to harmful queries asking to create a bomb, or that models like Stable Diffusion do not generate sexual images. I got my Ph.D. from Monash University in November 2023, under the supervision of Prof. Dinh Phung and Dr. Trung Le. My thesis can be found here.

Before that, I had one year working as Research Engineer at Credit AI Lab, Trusting Social, and two years working as Research Assistant at Singapore University of Technology and Design with Prof. Ngai Man Cheung and Dr. Trung Tran.

news

Oct 4, 2024	Excited to share another paper that I am very proud of. This paper is an extension of our NeurIPS 2024 paper, where we dive deeper into the impact of erasing one concept to the others, but this time, we focus on the choice of target concepts. The paper can be found here. Our paper’s name was inspired by the movie “Fantastic Beasts and Where to Find Them”. Hopefully, the reviewers enjoy it as much as the movie .
Sep 26, 2024	Proudly to share that our paper “Erasing Undesirable Concepts in Diffusion Models with Adversarial Preservation” has been accepted at NeurIPS 2024. We had a challenging rebuttal period, where we worked hard to address the feedback from some tough but silent reviewers. Fortunately, we had other reviewers who actively engaged with us, sought to understand our paper, and ultimately championed it. So, in this happy moment, I want to express my gratitude to the anonymous reviewers ❤️, as well as to my incredible collaborators from Monash and DST. We will soon update the paper with all the details and code. The pre-final version is available here with its slides. Hope you enjoy it.
Jun 28, 2024	I am thrilled and proud to see the Trustworthy Machine Learning project, on which I have been a key contributor since my PhD, being extended to a new 3-year project funded by the Department of Defense, Australia. The project will focus on various aspects of Trustworthy Generative Models, including alignment, safety, and robustness. This project is not only the first major grant on Generative AI in our DSAI department but also across the entire FIT at Monash University. 🎉 🎉 🎉
Nov 1, 2023	I officially become a Dr. today! My thesis “Enhancing Adversarial Robustness: Representation, Ensemble, And Distribution Approaches” is available here. Today is also my wedding anniversary Hooray!
Sep 22, 2023	Our paper “Optimal Transport Model Distributional Robustness” has been accepted to NeurIPS 2023! 🎉 (led by Van-Anh Nguyen)

latest posts

Jul 26, 2024	Connection between Flatness and Generalization
Jul 9, 2024	Trustworthy and Safety AI Resources
Jul 1, 2024	Comparing Implementations of Diffusion Models - HuggingFace Diffusers vs. CompVis Stable Diffusion

selected publications

2024

Erasing Undesirable Concepts in Diffusion Models with Adversarial Preservation

Tuan-Anh Bui, Vuong Long, Khanh Doan, and 4 more authors

NeurIPS 2024, 2024

Bib PDF Code Slides

@article{bui2024adversarial,
  title = {Erasing Undesirable Concepts in Diffusion Models with Adversarial Preservation},
  author = {Bui, Tuan-Anh and Long, Vuong and Doan, Khanh and Le, Trung and Montague, Paul and Abraham, Tamas and Phung, Dinh},
  journal = {NeurIPS 2024},
  year = {2024},
  url = {https://www.dropbox.com/scl/fi/qdfkfbe9lm6t3duef4clm/2024-AP.pdf?rlkey=6z3qzr8ch131vf49mrg7bz3u0&st=5cxpmjkc&dl=0},
}

Optimal Targets for Concept Erasure in Diffusion Models and Where To Find Them

Tuan-Anh Bui, Trang Vu, Long Vuong, and 4 more authors

Preprint, 2024

Bib PDF Code Slides

@article{bui2024adaptive,
  title = {Optimal Targets for Concept Erasure in Diffusion Models and Where To Find Them},
  author = {Bui, Tuan-Anh and Vu, Trang and Vuong, Long and Le, Trung and Montague, Paul and Abraham, Tamas and Junae, Kimand Phung, Dinh},
  journal = {Preprint},
  year = {2024},
  url = {https://www.dropbox.com/scl/fi/pf2190qpfpiuo05mhcqmi/Adaptive-Guide-Erasure.pdf?rlkey=63s7ruwqxhrdsc4i603gjmsri&st=68uk0267&dl=0},
}

Removing Undesirable Concepts in Text-to-Image Generative Models with Learnable Prompts

Tuan-Anh Bui*, Khanh Doan*, Trung Le, and 3 more authors

Preprint, 2024

Bib PDF Code Slides

@article{bui2024removing,
  title = {Removing Undesirable Concepts in Text-to-Image Generative Models with Learnable Prompts},
  author = {Bui${*}$, Tuan-Anh and Doan${*}$, Khanh and Le, Trung and Montague, Paul and Abraham, Tamas and Phung, Dinh},
  journal = {Preprint},
  year = {2024},
  url = {https://arxiv.org/abs/2403.12326},
}

Diversity-Aware Agnostic Ensemble of Sharpness Minimizers

Tuan-Anh Bui*, Vy Vo*, Tung Pham, and 2 more authors

Preprint, 2024

Bib PDF Code

@article{bui2024diversity,
  title = {Diversity-Aware Agnostic Ensemble of Sharpness Minimizers},
  author = {Bui${*}$, Tuan-Anh and Vo${*}$, Vy and Pham, Tung and Phung, Dinh and Le, Trung},
  journal = {Preprint},
  year = {2024},
  url = {https://arxiv.org/abs/2403.13204},
}

Optimal transport model distributional robustness

Van-Anh Nguyen, Trung Le, Tuan-Anh Bui, and 2 more authors

Advances in Neural Information Processing Systems, 2024

Bib PDF Code

@article{nguyen2024optimal,
  title = {Optimal transport model distributional robustness},
  author = {Nguyen, Van-Anh and Le, Trung and Bui, Tuan-Anh and Do, Thanh-Toan and Phung, Dinh},
  journal = {Advances in Neural Information Processing Systems},
  volume = {36},
  year = {2024},
  url = {https://proceedings.neurips.cc/paper_files/paper/2023/hash/4b91825aec2ed35150f1d3e8fb195556-Abstract-Conference.html},
}

2023

Generating Adversarial Examples with Task Oriented Multi-Objective Optimization

Tuan-Anh Bui, Trung Le, He Zhao, and 3 more authors

Transactions on Machine Learning Research, 2023

Bib PDF Code

@article{bui2023generating,
  title = {Generating Adversarial Examples with Task Oriented Multi-Objective Optimization},
  author = {Bui, Tuan-Anh and Le, Trung and Zhao, He and Tran, Quan and Montague, Paul and Phung, Dinh},
  journal = {Transactions on Machine Learning Research},
  issn = {2835-8856},
  year = {2023},
  url = {https://openreview.net/forum?id=2f81Q622ww},
}

2022

A Unified Wasserstein Distributional Robustness Framework for Adversarial Training

Tuan-Anh Bui, Trung Le, Quan Tran, and 2 more authors

In International Conference on Learning Representations, 2022

Bib PDF Code

@inproceedings{bui2021unified,
  title = {A Unified Wasserstein Distributional Robustness Framework for Adversarial Training},
  author = {Bui, Tuan-Anh and Le, Trung and Tran, Quan and Zhao, He and Phung, Dinh},
  booktitle = {International Conference on Learning Representations},
  year = {2022},
}

2021

Understanding and achieving efficient robustness with adversarial supervised contrastive learning

Tuan-Anh Bui, Trung Le, He Zhao, and 3 more authors

arXiv preprint arXiv:2101.10027, 2021

Bib PDF Code

@article{bui2021understanding,
  title = {Understanding and achieving efficient robustness with adversarial supervised contrastive learning},
  author = {Bui, Tuan-Anh and Le, Trung and Zhao, He and Montague, Paul and Camtepe, Seyit and Phung, Dinh},
  journal = {arXiv preprint arXiv:2101.10027},
  year = {2021},
}

2020

Improving adversarial robustness by enforcing local and global compactness

Tuan-Anh Bui, Trung Le, He Zhao, and 4 more authors

In European Conference on Computer Vision, 2020

Bib PDF Code Poster Slides

@inproceedings{bui2020improving,
  title = {Improving adversarial robustness by enforcing local and global compactness},
  author = {Bui, Tuan-Anh and Le, Trung and Zhao, He and Montague, Paul and deVel, Olivier and Abraham, Tamas and Phung, Dinh},
  booktitle = {European Conference on Computer Vision},
  pages = {209--223},
  year = {2020},
  organization = {Springer},
}

2019

Improving GAN with neighbors embedding and gradient matching

Ngoc-Trung Tran*, Tuan-Anh Bui*, and Ngai-Man Cheung

In Proceedings of the AAAI conference on artificial intelligence, 2019

Bib PDF Code

@inproceedings{tran2019improving,
  title = {Improving GAN with neighbors embedding and gradient matching},
  author = {Tran${*}$, Ngoc-Trung and Bui${*}$, Tuan-Anh and Cheung, Ngai-Man},
  booktitle = {Proceedings of the AAAI conference on artificial intelligence},
  volume = {33},
  number = {01},
  pages = {5191--5198},
  year = {2019},
}

2018

Dist-gan: An improved gan using distance constraints

Ngoc-Trung Tran, Tuan-Anh Bui, and Ngai-Man Cheung

In Proceedings of the European conference on computer vision (ECCV), 2018

Bib PDF Code

@inproceedings{tran2018dist,
  title = {Dist-gan: An improved gan using distance constraints},
  author = {Tran, Ngoc-Trung and Bui, Tuan-Anh and Cheung, Ngai-Man},
  booktitle = {Proceedings of the European conference on computer vision (ECCV)},
  pages = {370--385},
  year = {2018},
}