Our research aims to develop Machine Learning Algorithms that Make Sense in constrained and large-scale settings with applications in Advertising, Healthcare, Sustainability (Climate, Computing, Agricultural), Social Goods
[more about our research] [more about SAIL Research]

Selected Press Coverage: khoahocphattrien , Thanh Nien, VnExpress, BaoDauTu, DanTri, Vietnam.vn, Vietnam.vn, Yahoo Finance, Benzinga, Macau Business, Taiwan News, TNGlobal, VinGroup

We're open to research/industry collaborations in ML/CV/NLP:
  • Interested in ML research as Research Assistant, Intern, PhD, Postdoc? Please fill in the form here (w. your CV, transcript, level of commitment, & description of what types of projects you want to work on). Only shortlisted candidates will be contacted!
  • Other collaboration? Please reach out via email.


[07/2024] Accepted papers - [ECCV’24-a] on resilient backdoor attack and [ECCV’24-b] on backdoor attack after quantiziation(congrats Hoang V Pham and Tran Huynh/VinAI).
Congrats Lan H Tran for her acceptance to EPFL’s Master Program with scholarship (our first and forever female :heart: MAIL member).
[06/2024] :fire: I (w. co-leads Helen Nguyen/UIUC and Giang Phi/VinUni, and other collaborators) received the grand-prize award (£1M) at Trinity Challenge (in partnership with MIT Solve). Our work, using Generative AI to help farmers make better decisions and community managers have better antibiotics cluster surveilance to reduce antimicrobial resistance, is featured at several news outlets: Office Annoucement, Thanh Nien, VnExpress, BaoDauTu, DanTri, Vietnam.vn, Yahoo Finance, etc… Click to read more about our Farm2Vet Solution.
[05/2024] Accepted papers - [UAI’24] on lightweight, pluggable textual adversarial defense, and [ACL’24] on cold-start recommendation with personalized rating elicitation (hat off to Viet-Anh Nguyen/CUHK, Hieu Nguyen/VinAI, Duy C Hoang and Quang H Nguyen
Congrats Hoang V Pham for his acceptance to University of Warwick’s PhD Program
Congrats Nghia Dai Nguyen for his acceptance to UIUC PhD Program (co-advised)
[03/2024] Will serve as Invited Area Chair for NeurIPS and ACML 2024.
[03/2024] Will serve as Workshop Chair and Area Chair for ACML 2024.
[02/2024] Heng Ji & I gave talks at HCMUT/HCMUS (Ho Chi Minh, Jan 31st) and HUST/VNU/VinAI (Hanoi, Feb 01 and 02). We have immediate PhD (at VinUni or UIUC)/Research Assistants (at VinUni) positions to work on LLM Truthfulness and NLP for Molecular Discovery. I’m also recruiting students to work on Counterfactual Infererence/Explanation.
[01/2024] :fire: Our “AI for Environmental Intelligence: The Past, The Present, and The Future” Workshop proposal (w. Helen Nguyen, Nitesh Chawla, Alexandre d’Aspremont, Karina Ginn) accepted at CAI 2024 (June 25-27, 2024). More information here!
[01/2024] :fire: We’re granted 2 proposals by Vinuni-UIUC Smarthealth Center on Causal Inference in Healthcare and Evaluating Truthfulness/Misinformation of NLP/LLM (more details; we’re recruiting PhD Students/RAs)
[01/2024] Accepted paper - [ICLR’24] on same-inference-time Adversarial Defense (congrats Quang H Nguyen and Tung Pham/VinAI).
[01/2024] Will serve as Invited Workshop Reviewer for ICML 2024.
Congrats Hoang M Nguyen for his new journey as PhD Student at Saarland University
[12/2023] Will serve as Invited PC for ECCV and ICML 2024.

selected publications [full list]

  1. PREPRINT Non-Cooperative Backdoor Attacks in Federated Learning: A New Threat Landscape
    Tuan M Nguyen, Dung T Nguyen, Khoa D Doan, and Kok-Seng Wong
  2. PREPRINT Less is More: Sparse Watermarking in LLMs with Enhanced Text Quality
    Cao-Duy Hoang, Hung T. Q. Le, Rui Chu, Ping Li, Weijie Zhao, Yingjie Lao, and Khoa D Doan
  3. PREPRINT MetaLLM: A High-performant and Cost-efficient Dynamic Framework for Wrapping LLMs
    Quang H Nguyen, Cao-Duy Hoang, Juliette Decugis, Saurav Manchanda, Nitesh V Chawla, and Khoa D Doan
  4. PREPRINT Forget but Recall: Incremental Latent Rectification in Continual Learning
    Nghia D Nguyen, Hieu T Nguyen, Ang Li, Hoang V Pham, Viet Anh Nguyen, and Khoa D Doan
  5. UAI Cold-start Recommendation by Personalized Embedding Region Elicitation
    In The Conference on Uncertainty in Artificial Intelligence 2023
  6. PREPRINT Synthesizing Physical Backdoor Datasets: An Automated Framework Leveraging Deep Generative Models
    Sze Jue Yang, Chinh D La, Quang H Nguyen, Eugene Bagdasaryan, Kok-Seng Wong, Anh T Tran, Chee Seng Chan, and Khoa D Doan
  7. ACL-Findings Fooling the Textual Fooler via Randomizing Latent Representations
    Cao-Duy Hoang, Quang H Nguyen, Saurav Manchanda, Minlong Peng, Kok-Seng Wong, and Khoa D Doan
    In Findings of the Association for Computational Linguistics 2024
  8. ICLR Understanding the Robustness of Randomized Feature Defense Against Query-Based Adversarial Attacks
    Quang H Nguyen, Yingjie Lao, Tung Pham, Kok-Seng Wong, and Khoa D Doan
    In The Twelfth International Conference on Learning Representations 2024
  9. NeurIPS Iba: Towards irreversible backdoor attacks in federated learning
    Thuy Dung Nguyen, Tuan M Nguyen, Anh T Tran, Khoa D Doan, and Kok-Seng Wong
    Advances in Neural Information Processing Systems 2024
  10. EAAI Backdoor attacks and defenses in federated learning: Survey, challenges and future research directions
    Thuy Dung Nguyen, Tuan M Nguyen, Phi Le Nguyen, Hieu H Pham, Khoa D Doan, and Kok-Seng Wong
    Engineering Applications of Artificial Intelligence 2024
  11. SIGIR Asymmetric Hashing for Fast Ranking via Neural Network Measures
    Khoa D Doan, Shulong Tan, Weijie Zhao, and Ping Li
    In 46th International ACM SIGIR Conference on Research and Development in Information Retrieval 2023
  12. AAAI Defending backdoor attacks on vision transformer via patch processing
    Khoa D Doan, Yingjie Lao, and Ping Li
    In AAAI Conference on Artificial Intelligence 2023
  13. NeurIPS Marksman Backdoor: Backdoor Attacks with Arbitrary Target Class
    Khoa D Doan, Yingjie Lao, and Ping Li
    In Thirty-Sixth Conference on Neural Information Processing Systems 2022
  14. CVPR One Loss for Quantization: Deep Hashing with Discrete Wasserstein Distributional Matching
    Khoa D Doan, Peng Yang, and Ping Li
    In Conference on Computer Vision and Pattern Recognition 2022
  15. NeurIPS Backdoor Attack with Imperceptible Input and Latent Modification
    Khoa D Doan, Yingjie Lao, and Ping Li
    In Thirty-Fifth Conference on Neural Information Processing Systems 2021
  16. ICCV LIRA: Learnable, Imperceptible and Robust Backdoor Attacks
    Khoa D Doan, Yingjie Lao, Weijie Zhao, and Ping Li
    In International Conference on Computer Vision 2021
  17. SIGIR Interpretable Graph Similarity Computation via Differentiable Optimal Alignment of Node Embeddings
    Khoa D Doan, Saurav Manchanda, Suchismit Mahapatra, and Chandan K Reddy
    In 44th International ACM SIGIR Conference on Research and Development in Information Retrieval 2021
  18. WWW Efficient Implicit Unsupervised Text Hashing Using Adversarial Autoencoder
    Khoa D Doan, and Chandan K Reddy
    In Proceedings of The Web Conference 2020
  19. arXiv Gradient boosting neural networks: Grownet
    arXiv preprint arXiv:2002.07971 2020
  20. CIKM Adversarial Factorization Autoencoder for Look-Alike Modeling
    Khoa D Doan, Pranjul Yadav, and Chandan K Reddy
    In Proceedings of the 28th ACM International Conference on Information and Knowledge Management 2019
Majority of work done by MAIL/SAIL members!
Submission History shows the venues where the work has been submitted (🙃 including rejections 🙃). I hope some of my poor rejection/failure histories (record now is 10 rejections 😅) give you some encouragement to try again when things don't work out (don't give up -- good work doesn't need to be rushed)!

Open Office Hour

I will ocassionally be holding group open office hours (fully ONLINE) for *anyone*. Feel free to sign up to connect, chat, or ask any questions.

When I was a student, I was clueless sometimes (if not most of the time) and I had no idea how to get help. I hope that, via this modest effort, I can share some experience with you, as well as address some questions you may have, using my experience working in both industry and academia and applied and research projects, as well as experience in studying abroad in the US. I encourage to converse in English.

This effort is inspired by ML Collective

The brick walls are there for a reason. The brick walls are not there to keep us out. The brick walls are there to give us a chance to show how badly we want something -- Randy Pausch