Wenjing Lou is the W. C. English Endowed Professor of Computer Science at Virginia Tech and a Fellow of both the IEEE and the ACM. Her research interests cover many topics in the cybersecurity field, with her current research focusing on security and privacy problems in wireless networks, blockchain, trustworthy machine learning, and Internet of Things (IoT) systems. Prof. Lou is a highly cited researcher by the Web of Science Group. She received the Virginia Tech Alumni Award for Research Excellence in 2018, the highest university-level faculty research award. She received the IEEE INFOCOM Test-of-Time paper award in 2020 and IEEE INFOCOM Achievement Award in 2025. She is the TPC chair for IEEE INFOCOM 2019 and ACM WiSec 2020. She was the Steering Committee Chair for IEEE CNS conference from 2013 to 2020. She is currently the vice chair of IEEE INFOCOM and a steering committee member of IEEE CNS. She served as a program director at the US National Science Foundation (NSF) from 2014 to 2017.
Presentation Title:
Privacy Challenges in Federated Learning: From Data Leakage to Model Theft
Presentation Abstract:
While the success of machine learning has largely relied on centralized learning, which pools training data from multiple sources to a central location, federated learning offers a promising privacy-preserving alternative that enables institutions to collaboratively train models without sharing sensitive data. However, recent research has shown that even in federated learning, participant information can be inferred from model updates.
This talk will focus on the privacy challenges in federated learning. We will explain the state-of-the-art model inversion attacks capable of reconstructing participate data from model updates. We will explore the broader implications of these privacy threats and discuss the limitations of traditional privacy-enhancing technologies. Additionally, we will discuss concerns around model privacy and show how fingerprinting techniques can be designed to protect the intellectual property of machine learning models.