Preserving Data Privacy in Federated Learning - Xiaokui Xiao
Offered By: Association for Computing Machinery (ACM) via YouTube
Course Description
Overview
Explore the critical aspects of data privacy in federated learning through this 35-minute conference talk by Xiaokui Xiao. Delve into the fundamentals of federated learning, its operational mechanisms, and the challenges it presents to data privacy. Examine various approaches to preserving privacy, including local gradient methods, multi-party computation (MPC), trusted hardware, and differential privacy. Analyze experimental results and real-world examples, such as age distribution of customers, to understand the practical implications of these techniques. Investigate the concept of model privacy in vertical federated learning and discuss potential mitigation strategies. Conclude with insights into future work, including the development of privacy frameworks and new techniques, while addressing other pertinent issues in the field. Gain valuable knowledge from this presentation delivered at the Association for Computing Machinery (ACM) conference, with the speaker representing the National University of Singapore.
Syllabus
Introduction
What is Federated Learning
How Federated Learning Works
Local Gradient
Experimental Results
Basic Idea
Example
Using MPC
Trusted Hardware
Differential Privacy
Differential Privacy Limitations
Age Distribution of Customers
Model Privacy
Vertical Factory Learning
Mitigation
Hiding the model
Summary
Future Work
Privacy Framework
New Techniques
Other Issues
National University of Singapore
Questions
Taught by
Association for Computing Machinery (ACM)
Related Courses
Statistical Machine LearningCarnegie Mellon University via Independent Secure and Private AI
Facebook via Udacity Data Privacy and Anonymization in R
DataCamp Build and operate machine learning solutions with Azure Machine Learning
Microsoft via Microsoft Learn Data Privacy and Anonymization in Python
DataCamp