🏋🏻‍♂️ Bo Hui

I am a current Ph.D. student at the Johns Hopkins University advised by Prof. Yinzhi Cao. I received my M.S. in Security Informatics from Hopkins and B.E. in Software Engineering at Shandong University. My research interests lie in achieving high performance and privacy-preserving in Machine Learning. Check out my resume if you are interested.

• ✉️ Email: {firstname}.{lastname}@jhu.edu
• 👨🏻‍💻 Github: BHui97

📃 Publications

• PLeak: Prompt Leaking Attacks against Large Language Model Applications

  Bo Hui, Haolin Yuan, Neil Zhenqiang Gong, Philippe Burlina,and Yinzhi Cao
  In the Proceedings of The ACM Conference on Computer and Communications Security (CCS), 2024.
  Paper | Code

• Fortifying Federated Learning against Membership Inference Attacks via Client-level Input Perturbation

  Yuchen Yang, Bo Hui, Haolin Yuan, Neil Zhenqiang Gong ,and Yinzhi Cao
  To appear in the Annual IEEE/IFIP International Conference on Dependable Systems and Network (DSN), 2023.
  Paper | Code

• PrivateFL: Accurate, Differentially Private Federated Learning via Personalized Data Transformation

  Bo Hui*, Yuchen Yang*, Haolin Yuan*, Neil Zhenqiang Gong ,and Yinzhi Cao (* Equal Contributions)
  To appear in the Proceedings of USENIX Security Symposium, 2023
  Paper | Code

• Addressing Heterogeneity in Federated Learning via Distributional Transformation

  Bo Hui*, Haolin Yuan*, Yuchen Yang*, Philippe Burlina, Neil Zhenqiang Gong, and Yinzhi Cao (* Equal Contributions)
  In the Proceedings of European Conference on Computer Vision (ECCV), 2022
  Paper | Code

• Practical Blind Membership Inference Attack via Differential Comparisons

  Bo Hui*, Yuchen Yang, Haolin Yuan*, Philippe Burlina, Neil Zhenqiang Gong, and Yinzhi Cao (* Equal Contributions)
  In the Proceedings of Network & Distributed System Security Symposium (NDSS), 2021
  Paper | Code

🎲 Experiences

• Teaching Assistant, at the Johns Hopkins University, 2023.8--Now
• Research Assistant, at the Johns Hopkins University, 2020.3--Now
• Course Assistant, at the Johns Hopkins University, 2020.9--2020.12

This page was inspired by 🍂 Favonia and made with GitHub-like CSS.