Wenwei Zhao

Wenwei Zhao

Biography

Dr. Wenwei Zhao is a software engineer on Google’s Envoy AI Foundation team. She received her Ph.D. degree under Dr. Zhuo Lu at University of South Florida in 2026. Wenwei Zhao’s research interests include secure and trustworthy machine learning, distributed systems, and network security.

Interests
  • Secure and Trustworthy Machine Learning
  • Federated Learning and Machine Unlearning
  • Distributed and Networked Systems
  • Network and Systems Security
Education
  • PhD in Electrical Engineering, 2026

    University of South Florida

  • MS in Electrical and Computer Engineering, 2021

    Univerisity of Florida

  • BSc in Optoelectronics Information Science and Engineering, 2019

    Hefei University of Technology

Recent Publications

Quickly discover relevant content by filtering publications.
(2026). Adapter-Based Parameter-Efficient Adversarial Training for Enhanced Clean Accuracy. The ACM Workshop on Wireless Security and Machine Learning (WiSec-WiseML) 2026.

PDF Cite

(2026). Consistency-Preserving Logit Shaping for Robust Model Stealing Defense with Applications in Wireless Spectrum Security. The ACM Workshop on Wireless Security and Machine Learning (WiSec-WiseML) 2026.

PDF Cite

(2026). Malicious Forgetting: Backdoor Injection in Active Federated Unlearning and Countermeasure Design. IEEE Conference on Computer Communications (INFOCOM) 2026.

PDF Cite

(2026). Adversarial Update-Based Federated Unlearning for Poisoned Model Recovery. IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP) 2026.

PDF Cite

(2026). Equilibrium-Driven Vertical Federated Learning with Selective Privacy Protection. AAAI Conference on Artificial Intelligence 2026.

PDF Cite

(2024). Detecting Adversarial Spectrum Attacks via Distance to Decision Boundary Statistics. Infocom 2024.

PDF Cite

(2024). Understanding the Ineffectiveness of the Transfer Attack in Intrusion Detection System. Network Security Empowered by Artificial Intelligence.

PDF Cite

(2022). PCB component detection using computer vision for hardware assurance. Big Data and Cognitive Computing.

PDF Cite

(2018). Cyclically Interval Total Coloring of the One Point Union of Cycles. Open Journal of Discrete Mathematics.

PDF Cite

Professional Service

Journal Reviewer

  • IEEE Transactions on Information Forensics and Security (TIFS)
  • IEEE Transactions on Dependable and Secure Computing (TDSC)
  • IEEE/ACM Transactions on Networking (TON)
  • ACM Transactions on Privacy and Security (TOPS)
  • IEEE Transactions on Cognitive Communications and Networking (TCCN)
  • IEEE Transactions on Machine Learning in Communications and Networking (TMLCN)

Conference Reviewer

  • NeurIPS 2026
  • IEEE INFOCOM 2025

Contact