About Me
I’m a Ph.D. student in the Department of Electrical and Computer Engineering at the University of Maryland, College Park. My advisor is Prof. Ang Li. My research interests include Federated learning, Large Scale Models, Machine Learning security and privacy. I’m interested in discovering novel approaches to solve pratical problems in these fields.
Before coming to UMD, I was working as a research intern in Prof. Qian Wang’s NIS&P Lab at Wuhan University. I was also a research intern at Pennsylvania State University, under the supervision of Prof. Dongwon Lee and Dr. Thai Le.
Interests
- Federated Learning
- Large Scale Models
- Machine Learning security and privacy
Education
BSc in Cyber Science and Engineering, 2019-2023
Wuhan University
Ph.D. student of Electrical and Computer Engineering, 2023-
University of Maryland, College Park
Publications
indicates equal contribution.
(2024).
FLoRA: Federated Fine-Tuning Large Language Models with Heterogeneous Low-Rank Adaptations.
Thirty-Eighth Annual Conference on Neural Information Processing Systems (NeurIPS 2024).
(2024).
One Shot is All You Need: An Emergent Ability of Foundation Models in Federated Fine-Tuning.
Under Review of ICLR 2025.
(2024).
SHED: Shapley-Based Automated Dataset Refinement for Instruction Fine-Tuning.
Thirty-Eighth Annual Conference on Neural Information Processing Systems (NeurIPS 2024).
(2023).
FedHyper: A Universal and Robust Learning Rate Scheduler for Federated Learning with Hypergradient Descent.
The Twelfth International Conference on Learning Representations (ICLR 2024).
(2023).
UPTON: Preventing Authorship Leakage from Public Text Release via Data Poisoning.
Findings of The 2023 Conference on Empirical Methods in Natural Language Processing (EMNLP-Findings).
(2023).
Moderator: Moderating Text-to-Image Diffusion Models through Fine-grained Context-based Policies.
The 31st ACM Conference on Computer and Communications Security (CCS 2024 Distinguished Paper Award).
(2023).
NetGuard: Protecting Commercial Web APIs from Model Inversion Attacks using GAN-generated Fake Samples.
The World Web Conference (WWW 2023).
(2023).
Kaleidoscope: Triggering Backdoor with RGB Filters.
IEEE Transactions on Dependable and Secure Computing (TDSC).
(2022).
A GAN-based Defense Framework against Model Inversion Attacks.
IEEE Transactions on Information Forensics and Security (TIFS).
(2022).
KERBNET: A QoE-aware Kernel-Based Backdoor Attack Framework.
IEEE Transactions on Dependable and Secure Computing (TDSC).
Experience
Ph.D. Student
University of Maryland, College Park
Advised by Prof. Ang Li in CASE Lab.
Research Intern
Pennsylvania State University
Advised by Prof. Dongwon Lee and Dr. Thai Le in PIKE Lab.
Research Intern
Wuhan University
Advised by Prof. Qian Wang in NIS&P Lab.
Undergraduate
Wuhan University
Got 3.92 GPA, Rank 7/124.
Contact
- ziyaow@umd.edu
- +1 2409303265
- 7999 Regents Dr. College Park, College Park, MD 20742
- Ziyao Wang
- Zoom Me