Recent Publications

• Deep Learning with Plausible Deniability [PDF (OpenReview)]
  In Neural Information Processing Systems (2025)
  Wenxuan Bao, Shan Jin, Hadi Abdullah, Anderson C. A. Nascimento, Vincent Bindschaedler, Yiwei Cai
• Inference Attacks for X-Vector Speaker Anonymization [PDF]
  In IEEE Security and Privacy Workshops (2025)
  Luke A. Bauer, Wenxuan Bao, Malvika Jadhav, Vincent Bindschaedler
• Provably Secure Covert Messaging Using Image-based Diffusion Processes [PDF]
  In IEEE Conference on Secure and Trustworthy Machine Learning (2025)
  Luke A. Bauer, Wenxuan Bao, Vincent Bindschaedler
• R+R: Towards Reliable and Generalizable Differentially Private Machine Learning [PDF (Extended Version)]
  In Annual Computer Security Applications Conference (2024)
  Wenxuan Bao, Vincent Bindschaedler
• DP-Mix: Mixup-based Data Augmentation for Differentially Private Learning [PDF]
  In Neural Information Processing Systems (2023)
  Wenxuan Bao, Francesco Pittaluga, Vijay Kumar B G, Vincent Bindschaedler