Brian Jay Tang

Brian Jay Tang

1st Year PhD Student

Ann Arbor, MI

About Me

I’m a 1st year Computer Science PhD student at the University of Michigan and a member of the Real-Time Computing Lab. My research focuses on the security, privacy, and ethics of machine learning systems.

Please contact me via byron123t [at] gmail [dot] com or bjaytang [at] umich [dot] edu. I’m always willing to meet up in person as well if you happen to be on campus or in the Chicago area.


Research Assistant

Fall 2021 - Present · University of Michigan

Research Assistant

Fall 2018 - Summer 2021 · University of Wisconsin - Madison

Involved in 4 research projects, I contributed with experiment design, writing, dataset creation, literature surveys, and more.

Software Engineering Intern

Summer 2019 - Summer 2019 · Roblox

Using test-driven development, I designed and implemented core features for Roblox Studio’s script editor.

Software Engineering Intern

Summer 2018 - Summer 2018 · Optum

I designed and developed a web application which aggregates and visualizes over 50 million records from security scans and databases.


Ph.D. in Computer Science

2021 - 2026 · University of Michigan

Thesis: To be determined

M.S. in Computer Science

2021 - 2023 · University of Michigan

Thesis: To be determined

B.S. in Computer Science

2017 - 2020 · University of Wisconsin - Madison


Journal Articles

2021. H Rosenberg, B Tang, K Fawaz, S Jha. Fairness Properties of Face Recognition and Obfuscation Systems. arXiv preprint arXiv:2108.02707.

2019. V Chandrasekaran, B Tang, N Papernot, K Fawaz, S Jha, X Wu. Rearchitecting Classification Frameworks For Increased Robustness. arXiv preprint arXiv:1905.10900.


2020. V Chandrasekaran, C Gao, B Tang, K Fawaz, S Jha, S Banerjee. Face-off: Adversarial Face Obfuscation. Proceedings on Privacy Enhancing Technologies 2021 (2), 369-390.


Creating a Privacy-Aware Conversational Robot

As social robots develop better conversational capabilities, users need to trust such robots with their conversations and data. Privacy issues arise when robots have a different notion of privacy than the user. For example, a robot may share details from a sensitive conversation with another user. We provide a framework for disclosure in multi-user conversational settings which is able to align with users' privacy preferences.

Fairness Properties of Face Recognition and Obfuscation Systems

As more face obfuscation systems such as Face-Off have emerged (Low-Key, FAWKES, FoggySight, etc.), we need to understand whether these systems operate fairly for each demographic. Since face recognition systems are known to have demographic fairness issues particularly with regards to skin tone and sex, we explore fairness in face recognition and face obfuscation.

Face-off: Adversarial Face Obfuscation

While face recognition has been useful to social media platforms and users, this technology poses significant threats to user privacy. Malicious entities or overly-curious service providers can surveil users to an uncomfortably accurate level. We propose Face-Off, a privacy-preserving framework that induced adversarial perturbations to a user’s face with the goal of evading face recognition services.

Rearchitecting Classification Frameworks For Increased Robustness

With autonomous vehicles becoming reliant on machine learning and computer vision, it is important to discuss how defenses against adversarial attacks can leverage real world features. We construct a classification paradigm that leverages invariances found in data to improve the robustness vs. accuracy trade-off.


Mandarin Chinese


  • Cooking
  • Reading
  • Investing
  • Video games, tabletop games, board games
  • Anime, manga
  • Skateboarding, biking
  • Meditation, taijiquan