Wenxuan Bao
About Me
Hello, my name is Wenxuan Bao (包文轩). I am a Staff Research Scientist at Visa Research, where my work focuses on AI agents security, privacy and reliability.
I earned my PhD from the CISE Department at the University of Florida in December 2025. During my PhD, I was part of the Florida Institute for Cybersecurity Research (FICS), advised by Dr. Vincent Bindschaedler.
Research Interests
Privacy-Preserving Machine Learning, Differential Privacy, AI Agents Security, Privacy and Reliability.
News
- [2026.02] I joined Visa Research as a Staff Research Scientist!
- [2025.10] I have been named as Top Reviewer for NeurIPS 2025!
- [2025.09] Our work “Deep Learning with Plausible Deniability” is accepted in NeurIPS 2025!
- [2025.09] Our work “Enabling Plausible Deniability in Flash-based Storage through Data Permutation” is accepted in ACSAC 2025!
Publications
Deep Learning with Plausible Deniability
Wenxuan Bao, Shan Jin, Hadi Abdullah, Anderson C. A. Nascimento, Vincent Bindschaedler and Yiwei Cai
NeurIPS, 2025.
Enabling Plausible Deniability in Flash-based Storage through Data Permutation.
Weidong Zhu, Wenxuan Bao, Vincent Bindschaedler, Sara Rampazzi and Kevin R. B. Butler
ACSAC, 2025.
Provably Secure Covert Messaging Using Image-based Diffusion Processes
Luke A. Bauer, Wenxuan Bao, and Vincent Bindschaedler
SaTML, 2025.
Inference Attacks for X-Vector Speaker Anonymization
Luke A. Bauer, Wenxuan Bao, Malvika Ranjitsinh Jadhav and Vincent Bindschaedler
IEEE S&P Workshops, 2025.
R+R: Towards Reliable and Generalizable Differentially Private Machine Learning.
Wenxuan Bao and Vincent Bindschaedler
ACSAC, 2024.
DP-Mix: Mixup-based Data Augmentation for Differentially Private Learning.
Wenxuan Bao, Francesco Pittaluga, Vijay Kumar B G, and Vincent Bindschaedler
NeurIPS, 2023.
On the Importance of Architecture and Feature Selection in Differentially Private Machine Learning.
Wenxuan Bao, Luke A. Bauer, and Vincent Bindschaedler
arXiv, 2022.