Generative Adversarial Models for Privacy and Fairness
Offered By: Simons Institute via YouTube
Course Description
Overview
Syllabus
Intro
Zero-sum games
Generative Adversarial Networks (GANS)
Why not using GANs as they are?
Membership inference attacks for GANS
Differential Privacy (DP) to the rescue!
TensorFlow Privacy
Differentially private GANS (DP-GAN)
DP-GAN: noisy Wasserstein GAN
DP-GAN results
Context-aware fair data publishing
Empirical risk minimization with MI?
Generative Adversarial Privacy & Fairness (GAPF)
Example: GAPF under log-loss
Data-driven GAPF
Penalty method
Real-life data: GENKI dataset
Adversary's neural network
Feedforward Neural Network (FNN) encoder
Transposed Convolution Neural Network (TCNNP) encoder
GENKI fairness vs utility
Siamese-GAPF (S-GAPF) What if the sensitive label can take many values?
Real-life data: HAR dataset
HAR fairness vs utility
Gaussian mixture data model
Taught by
Simons Institute
Related Courses
Creative Applications of Deep Learning with TensorFlowKadenze Creative Applications of Deep Learning with TensorFlow III
Kadenze Creative Applications of Deep Learning with TensorFlow II
Kadenze 6.S191: Introduction to Deep Learning
Massachusetts Institute of Technology via Independent Learn TensorFlow and deep learning, without a Ph.D.
Google via Independent