About me

In 2025, I am honored to have been awarded the Melbourne Research Scholarship for talented individuals. I am currently pursuing my PhD at the University of Melbourne (ranked 19* worldwide), under the supervision of Dr. Bach Le Dinh Xuan and Dr. Van-Thuan Pham.

Previously, I graduated with a Bachelor's degree in Computer Science from Vietnam National University in 2022, where I was supervised by Dr. Tran Quoc Long, Director of the Institute for Artificial Intelligence.

From 2022 to 2025, I joined the AI Residency Program at the FPT AI Center**, working alongside outstanding young researchers across Vietnam. With invaluable mentorship from Dr. Nghi Bui (Salesforce Senior Scientist; Product Owner & Lab Manager at FPT Software) and Dr. Quang Pham (Research Scientist at A*STAR), I published research papers at leading international conferences, including ICLR, EMNLP, and NAACL.

Beyond academia, I am an active contributor to open-source projects and always welcome opportunities for collaboration. The best way to reach me is via email.

* According to QS World University Rankings 2025
** Listed among the Top 50 AI Labs worldwide

Research focus

My research lies at the intersection of large language models (LLMs), software engineering, and cybersecurity. I am particularly interested in making AI-powered code generation more secure, reliable, and trustworthy.

Specifically, I focus on:
Reinforcement Learning for Secure Code designing RL-based methods (e.g., PPO, DPO, multi-agent RL) to align LLMs with secure software engineering practices.
Adversarial Robustness developing fine-tuning and adversarial training strategies to reduce vulnerabilities in LLM-generated code.
Benchmarking & Evaluation creating new benchmarks to measure threat awareness, vulnerability detection, and resilience of LLMs in real-world scenarios.
Automation in Secure Software Development building scalable frameworks that integrate security into LLM-powered coding assistants, reducing reliance on human oversight.

Broadly, my goal is to advance secure and autonomous software engineering, ensuring that the next generation of AI systems can empower developers without amplifying cybersecurity risks.

Education

Oct 2025 - now

Doctor of Philosophy, Engineering and IT

The University of Melbourne, Australia
  • Topic: Secure AI for software development
  • Melbourne Research Scholarship
2018 - 2022

Bachelor of Computer Science

Vietnam National University, Hanoi
  • Honours degree
  • CGPA 3.61

Experience & Past Affiliation

Jul 2022 - Aug 2025

AI Resident

FPT Software AI Center, FPT
May 2020 - Oct 2022

Undergraduate Student Researcher

Vietnam National University, Hanoi
Apr 2021 - Jul 2021

Machine Learning Intern

Viettel Digital Talent Program

Highlight Publications

CodeMMLU: A Multi-Task Benchmark for Assessing Code Understanding Capabilities of CodeLLMs

ICLR 2025
Dung Nguyen Manh, Thang Phan Chau, Nam Le Hai, Thong T. Doan, Nam V. Nguyen, Quang Pham, and Nghi D. Q. Bui

The Vault: A Comprehensive Multilingual Dataset for Advancing Code Understanding and Generation

EMNLP 2023
Dung Nguyen Manh, Nam Le Hai, Anh T. V. Dau, Anh Minh Nguyen, Khanh Nghiem, Jin Guo, and Nghi D. Q. Bui