EIFFeL: Ensuring Integrity for Federated Learning

October 20, 2022
3:00-4:15 pm ET
Cummings 270, Zoom
Speaker: Amrita Roy Chowdhury, University of California San Diego
Host: Johes Bater

Abstract

Federated learning (FL) enables clients to collaborate with a server to train a machine learning model. To ensure privacy, the server performs secure aggregation of model updates from the clients. Unfortunately, this prevents verification of the well-formedness (integrity) of the updates as the updates are masked. Consequently, malformed updates designed to poison the model can be injected without detection. In this talk, I will formalize the problem of ensuring bothupdate privacy and integrity in FL and present a new system, EIFFeL, that enables secure aggregation of verified updates. EIFFeL is a general framework that can enforce arbitrary integrity checks and remove malformed updates from the aggregate, without violating privacy. Further, EIFFeL is practical for real-world usage. For instance, with 100 clients and 10% poisoning, EIFFeL can train an MNIST classification model to the same accuracy as that of a non- poisoned federated learner in just 2.4s per iteration.

Bio:

Amrita Roy Chowdhury is a CRA/CCC CIFellow at UCSD, working with Prof. Kamalika Chaudhuri. She graduated with her PhD from UW Madison and was advised by Prof. Somesh Jha. She completed her Bachelor of Engineering in Computer Science from the Indian Institute of Engineering Science and Technology, Shibpur where she was awarded the President of India Gold Medal. Her work explores the synergy between differential privacy and cryptography through novel algorithms that expose the rich interconnections between the two areas, both in theory and practice. She has been recognized as a Rising Star in EECS in 2020 and 2021, and a Facebook Fellowship finalist, 2021. She has also been selected as a UChicago Rising Star in Data Science, 2021.

Please join meeting in Cummings 270 or via Zoom.

Join Zoom Meeting: https://tufts.zoom.us/j/96038251227

Meeting ID: 960 3825 1227

Passcode: see colloquium email

Dial by your location: +1 646 558 8656 US (New York)

Meeting ID: 960 3825 1227

Passcode: see colloquium email