I work in the SAND Lab at
the University of Chicago and am advised by
Dr. Ben Zhao and Dr. Heather Zheng. I am interested in the intersection of machine learning and privacy. Currently, my research explores the limitations, vulnerabilities, and privacy implications of neural networks.
Publications
Fawkes: Protecting Personal Privacy against Unauthorized Deep Learning Models Shawn Shan, Emily Wenger (co-first author), Jiayun Zhang, Huiying Li, Haitao Zheng, Ben Y. Zhao USENIX Security Symposium (USENIX Security'20), Boston, MA, August 2020 [Paper][Website]
Gotta Catch 'em All: Using Honeypots to Catch Adversarial Attacks on Neural Networks Shawn Shan, Emily Wenger, Bolun Wang, Bo Li, Haitao Zheng, Ben Y. Zhao Proceedings of ACM Conference on Computer and Communications Security (CCS). Orlando, FL, November 2020 [Paper]
Backdoor Attacks Against Facial Recognition in the Physical World Emily Wenger, Josephine Passananti, Yuanshun Yao, Haitao Zheng, Ben Y, Zhao In Submission
Blacklight: Defending Black-Box Adversarial Attacks on Deep Neural Networks Huiying Li, Shawn Shan, Emily Wenger, Jiayun Zhang, Haitao Zheng, Ben Y. Zhao In Submission
Piracy Resistant Watermarks for Deep Neural Networks Huiying Li, Emily Wenger, Ben Y. Zhao, Haitao Zheng In Submission
News
November 2020: Had a fun conversation about the potential/problems of facial recognition on the ERLC's WeeklyTech Podcast.
July/August 2020: Fawkes received a lot of media attention! It was covered by the New York Times, The Verge, and The Register, among others. For a full list of press coverage, please visit the Fawkes website.
