Projects per year
Personal profile
Research interests
I am a 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.
Research area keywords
- Trustworthy Machine Learning
- Generative Models
Collaborations and top research areas from the last five years
Recent external collaboration on country/territory level. Dive into details by clicking on the dots or
Projects
- 1 Active
-
TMLGenAI: Trustworthy Generative AI: Towards Safe and Aligned Foundation Models
Phung, D. (Primary Chief Investigator (PCI)), Vu, T. (Chief Investigator (CI)), Qu, L. (Chief Investigator (CI)), Le, T. (Chief Investigator (CI)), Haffari, R. (Chief Investigator (CI)), Webb, G. (Chief Investigator (CI)), Nicholson, A. (Chief Investigator (CI)), Ke, Q. (Chief Investigator (CI)), Cai, J. (Chief Investigator (CI)) & Bui, T. (Chief Investigator (CI))
11/06/24 → 10/07/26
Project: Research
Research output
- 7 Conference Paper
-
Erasing Undesirable Concepts in Diffusion Models with Adversarial Preservation
Bui, A., Vuong, L., Doan, K., Le, T., Montague, P., Abraham, T. & Phung, D., 2024, NeurIPS Proceedings - Advances in Neural Information Processing Systems 37 (NeurIPS 2024). Globerson, A., Mackey, L., Belgrave, D., Fan, A., Paquet, U., Tomczak, J. & Zhang, C. (eds.). San Diego CA USA: Neural Information Processing Systems (NIPS), 29 p. (Advances in Neural Information Processing Systems; vol. 37).Research output: Chapter in Book/Report/Conference proceeding › Conference Paper › Research › peer-review
Open AccessFile -
Global-Local Regularization Via Distributional Robustness
Phan, H., Le, T., Phung, T., Bui, A., Ho, N. & Phung, D., 2023, Proceedings of The 26th International Conference on Artificial Intelligence and Statistics. Ruiz, F., Dy, J. & van de Meent, J.-W. (eds.). London UK: Proceedings of Machine Learning Research (PMLR), Vol. 206. p. 7644-7664 21 p.Research output: Chapter in Book/Report/Conference proceeding › Conference Paper › Research › peer-review
Open Access8 Citations (Scopus) -
Optimal Transport Model Distributional Robustness
Nguyen, V.-A., Le, T., Bui, A. T., Do, T.-T. & Phung, D., 2023, Advances in Neural Information Processing Systems 36 (NeurIPS 2023). Oh, A., Naumann, T., Globerson, A., Saenko, K., Hardt, M. & Levine, S. (eds.). San Diego CA USA: Neural Information Processing Systems (NIPS), 14 p. (Advances in Neural Information Processing Systems; vol. 36).Research output: Chapter in Book/Report/Conference proceeding › Conference Paper › Research › peer-review
Open AccessFile1 Citation (Scopus) -
A unified Wasserstein distributional robustness framework for adversarial training
Bui, T. A., Le, T. & Phung, D., 2022, International on Learning Representation (ICLR) 2022. LeCun, Y. (ed.). USA: OpenReview, 25 p.Research output: Chapter in Book/Report/Conference proceeding › Conference Paper › Research › peer-review
Open AccessFile26 Citations (Scopus) -
On global-view based defense via adversarial attack and defense risk guaranteed bounds
Le, T., Bui, T., Le, T., Zhao, H., Montague, P., Tran, Q. & Phung, D., 2022, Proceedings of the 25th International Conference on Artificial Intelligence and Statistics (AISTATS) 2022. Camps-Valls, G., J. R. Ruiz, F. & Valera, I. (eds.). London UK: Proceedings of Machine Learning Research (PMLR), Vol. 151. p. 11438-11460 23 p.Research output: Chapter in Book/Report/Conference proceeding › Conference Paper › Research › peer-review
Open AccessFile