Research & Innovation

Three Stevens Professors Earn NSF Grant of $699,540 to Investigate Fair Privacy

The team will explore how advances in machine learning can create fairer privacy outcomes across demographics

Photo of Stevens grant awardees

Principal Investigator (PI) Hui (Wendy) Wang, associate professor in the Department of Computer Science (CS); and Co-PIs Jun Xu, CS assistant professor; and Yu Tao, associate professor of social sciences in the College of Arts and Letters recently received an award from the Secure and Trustworthy Computing Program of National Science Foundation in the amount of $699,540. Their project, entitled “SaTC: CORE: Medium: Privacy for All: Ensuring Fair Privacy Protection in Machine Learning,” will address the core issues of fair privacy from both technical and social perspectives.

Advances in the field of artificial intelligence and machine learning have resulted in algorithms and technologies for improving cybersecurity. However, machine learning is also vulnerable to new and sophisticated privacy attacks that leak information about the data used for learning and prediction. Privacy attacks can be discriminatory in the sense that they can have a higher success rate for certain demographic groups (e.g., females) than other groups (e.g., males). However, none of the existing defense mechanisms against these attacks consider such disparate vulnerabilities, and as such, perform disparate efforts across different groups. This raises the serious concern of fair privacy—that is, how can we ensure that all groups and individuals are protected equitably?

Wang, Xu, and Tao’s project will address the core issues of fair privacy from both technical and social angles by investigating five research perspectives. Their findings will inform new curricula at Stevens, involving students in the latest cutting-edge research in security, privacy, and machine learning.

Learn more about computer science at Stevens: