Yizhen Wang

Staff Research Scientist 

Research Areas: Adversarial Machine Learning, Model Robustness

Yizhen Wang, Visa Research scientist.

Biography

Dr. Yizhen Wang joined Visa Research as a Staff Research Scientist in April 2020. Yizhen received his Ph.D. in Computer Science at University of California San Diego in 2020. His Ph.D. thesis was on robust machine learning in adversarial settings with the focus of building defense mechanisms with theoretical guarantee.

As a member of the Security team, his research interests are to identify security threats in machine learning systems and to design robust learning algorithms in various adversarial settings including test-time adversarial attack, data poisoning attack and backdoor attack. He is also interested in using machine learning techniques to detect and fix system security problems. He has published papers in international learning conferences and database conferences including International Conference on Machine Learning (ICML) and Association for Computing Machinery's Special Interest Group on Management of Data (SIGMOD).

Thesis

  • Wang, Y., (2020) Robust Learning with Provable Guarantee. UC San Diego.

Conferences

  • Wang, Y., Jha, S., & Chaudhuri, K. (2018, July). Analyzing the robustness of nearest neighbors to adversarial examples. In International Conference on Machine Learning (pp. 5133-5142).
  • Song, S., Wang, Y., & Chaudhuri, K. (2017, May). Pufferfish privacy mechanisms for correlated data. In Proceedings of the 2017 ACM International Conference on Management of Data (pp. 1291-1306).