About me

Welcome to my profile!

Hello, I’m Kieu Dang
πŸŽ“ PhD Student in Cybersecurity with a focus on LLMs.
🏫 State University of New York at Albany (SUNY Albany)
πŸ“ New York, USA

πŸ”¬ Research Interests:
- Trustworthy Machine Learning and AI
- Privacy-Preserving Machine Learning
- Adversarial Robustness and Watermarking

Education

πŸŽ“ PhD Student in Cybersecurity, State University of New York at Albany, USA (Aug 2024 – Present)
- Cumulative GPA: 4.00/4.00.
- Research Focus: Trustworthy Machine Learning and AI through the lens of Privacy and Security.

πŸŽ“ Master in Analytics, Applied Machine Intelligence, Northeastern University, USA (Aug 2021 – Jul 2023)
- Valedictorian of Fall 2021 cohort.
- Cumulative GPA: 4.00/4.00.
- Thesis: Improving Safety through the Integration of Multi-sensor Fusion and Deep Learning-based Object Detection.

Research Overview

My research explores the intersection of Trustworthy AI and Privacy-Preserving Technologies, aiming to develop mechanisms that enhance the security, privacy, and robustness of large language models. I collaborate with industry and academic partners to deploy and evaluate adversarial robustness, watermarking techniques, and privacy-preserving frameworks in real-world AI systems.

Recent Updates

πŸ† 11/2025: Our proposal β€œScalable Watermarking for LLM Outputs: IP Protection and Attribution on AIU Spyre” was selected as a 2025 CEAIS Seed Grant awardee (IBM Center for Emerging Artificial Intelligence Systems).
πŸ“œ 10/2025: My watermark patent is accepted on October 8, 2025.
πŸŽ‰ 09/2025: I am happy to share that my research paper \delta-STEAL: LLM Stealing Attack with Local Differential Privacy has been accepted at ACML 2025.
πŸš€ Summer 2025: Mentoring 6 undergraduate students on LLM Watermarking at SUNY Albany.
πŸ† 04/2025: Received Second Prize for Best Poster at NTIR 2025.

Contact

πŸ“§ vdang@albany.edu
πŸ“° Medium
πŸ§‘β€πŸ’» GitHub
πŸŽ“ Google Scholar

Thank you!