Tuan-Anh Bui

Machine Learning Researcher in Generative AI and Trustworthy Machine Learning

personal_images/macedon_3.jpg

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 :joy:.
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 :joy: Hooray!
Sep 22, 2023 Our paper “Optimal Transport Model Distributional Robustness” has been accepted to NeurIPS 2023! 🎉 (led by Van-Anh Nguyen)

latest posts

selected publications

2024

  1. op4.gif
    Erasing Undesirable Concepts in Diffusion Models with Adversarial Preservation
    Tuan-Anh Bui, Vuong Long, Khanh Doan, and 4 more authors
    NeurIPS 2024, 2024
  2. op5.gif
    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
  3. op1.gif
    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
  4. op2.gif
    Diversity-Aware Agnostic Ensemble of Sharpness Minimizers
    Tuan-Anh Bui*, Vy Vo*, Tung Pham, and 2 more authors
    Preprint, 2024
  5. op3.gif
    Optimal transport model distributional robustness
    Van-Anh Nguyen, Trung Le, Tuan-Anh Bui, and 2 more authors
    Advances in Neural Information Processing Systems, 2024

2023

  1. omg3.gif
    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

2022

  1. omg2.gif
    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

2021

  1. omg5.gif
    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

2020

  1. omg6.gif
    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

2019

  1. omg7.gif
    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

2018

  1. omg8.gif
    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