Distinguished Lecture Series: Wenke Lee, Regents’ Professor and the John P. Imlay Jr. Chair at Georgia Tech
Date & Time: November 18, 2024 from 12:00 PM - 01:15 PM
Location: E202 Westgate Building
Watch this talk below.
“Privacy and Reliability Issues of Artificial Intelligence (AI) Systems”
Recent advances in AI promise to change virtually all aspects of our lives; however, it’s important to first examine why and how AI should be used for critical applications. In this talk, Lee will discuss the privacy issues in biometric-based authentication and surveillance, deepfakes, and the logical reasoning capabilities of LLM in the context of SAT solving.
State-of-the-art deep learning solutions are now used for face-based and voice-based authentication. However, conventional biometric authentication (e.g., access control to a building) requires the enrollment data of a user to be stored in a remote server—unprotected—for comparison at authentication time. Lee’s team has developed a system called Justitia to provide privacy-preserving biometric-based authentication. At enrollment time, a client device processes a user’s facial image with a DL pipeline, derives encryption keys from the face data, and uses the keys to encrypt some random secrets. The server only stores the encrypted secrets and the hash of the secrets and authenticates a user if the client device can decrypt the secrets and send the correct hash back, essentially making biometric authentication like password-based authentication.
There are privacy concerns in biometric-based surveillance, where the process of identifying persons of interest involves using the images of everybody on the scene. Lee’s team has developed a privacy-preserving biometric search approach called Fuzzy Labeled Private Set Intersection, where the server holding a large biometric database learns nothing about the query or the result, and the querier also learns nothing about the database other than the query’s match(es).
Lee will also share his thoughts on the “arms race” involving deepfakes in biometric-based applications and beyond (e.g., fake video announcements Finally, as to the question “What can LLMs do (well)?” Lee will share recent work on formally showing how a transformer can be programmed to perform SAT solving and empirically evaluating whether it can be trained to do so.
About the Speaker
Wenke Lee is a Regents’ Professor and the John P. Imlay Jr. Chair at Georgia Tech. His research interests include systems and network security, malware analysis, applied cryptography and machine learning, Lee holds a doctorate in computer science from Columbia University and is an ACM fellow and an IEEE fellow.