This course covers the learning outcomes and goals of preserving data privacy in federated learning. It teaches skills such as understanding federated learning, implementing local gradient techniques, utilizing trusted hardware, applying differential privacy, and exploring model privacy. The teaching method includes theoretical explanations, practical examples, and discussions on experimental results. The intended audience for this course is individuals interested in data privacy, federated learning, and machine learning techniques.
Preserving Data Privacy in Federated Learning - Xiaokui Xiao
Association for Computing Machinery (ACM) via YouTube
Overview
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
Reviews
4.0 rating, based on 1 Class Central review
-
Rahman GamerVery Good Explanation, Privacy, Local LGD, SGD, Global GD, Two steps were very good add Local GD and Adding noise. Future goal also very interesting. Code demonstration would make it more perfect. Thanks
