Privacy Budget Scheduling
Offered By: USENIX via YouTube
Course Description
Overview
Explore privacy budget scheduling in machine learning through this OSDI '21 conference talk. Delve into the challenges of managing differential privacy (DP) in model training to prevent information leakage. Learn about PrivateKube, an extension to Kubernetes that treats privacy as a manageable resource alongside traditional compute resources. Discover the Dominant Private Block Fairness (DPF) algorithm, designed to handle the non-replenishable nature of privacy budgets. Examine the talk's evaluation of PrivateKube and DPF on microbenchmarks and an ML workload, demonstrating how DPF allows for training more models under the same global privacy guarantee. Gain insights into the complexities of balancing privacy concerns with machine learning model development in this informative presentation.
Syllabus
Privacy Budget Scheduling
Example: Messaging App
What Can Leak?
Is Differential Privacy (DP) the Solution?
DP at Individual Model Level
Problem: Privacy Loss Accumulates
Solution: DP at Workload Level
Our Vision: Privacy as a Compute Resource
PrivateKube
Architecture
Outline
Problem: Privacy is not Replenishable
Dominant Privacy Fairness (DPF)
DPF Example
DPF Properties
Methodology Questions How does DPF compare to baseline schedulers? How does the DP semantic impact OPF?
Conclusion
Taught by
USENIX
Related Courses
Private Stochastic Convex Optimization: Optimal Rates in Linear TimeAssociation for Computing Machinery (ACM) via YouTube ABY3 - A Mixed Protocol Framework for Machine Learning
Association for Computing Machinery (ACM) via YouTube Protect Privacy in a Data-Driven World - Privacy-Preserving Machine Learning
RSA Conference via YouTube Privacy-Preserving Algorithms for Decentralised Collaborative Learning - Dr Aurélien Bellet
Alan Turing Institute via YouTube CryptGPU: Fast Privacy-Preserving Machine Learning on the GPU
IEEE via YouTube