Lecture

Machine Learning and Privacy

In course

Sunt aute eu voluptate consectetur ex. Consequat laboris consectetur exercitation minim minim ad quis commodo qui Lorem do nostrud irure. Magna occaecat dolor excepteur dolore dolor officia mollit. Cillum eu ullamco et cupidatat cillum. In irure cillum laborum do dolor.

Description

This lecture covers Federated Machine Learning, focusing on the setup where clients train a global model without sharing their data. It discusses adversarial models, membership and property inference attacks, defenses, and privacy risks. Additionally, it explores Differential Privacy in Machine Learning, including techniques like Objective Perturbation, Output Perturbation, and Gradient Perturbation, as well as the challenges of advanced composition and evaluating differentially private learning.

Instructors (2)

proident mollit commodo elit

Fugiat labore proident esse labore eu irure qui ad nulla sunt non Lorem. Mollit magna sit labore in mollit. Voluptate in aliquip nisi ex laborum. Deserunt sint deserunt pariatur laboris adipisicing amet velit non magna incididunt reprehenderit pariatur.

aute elit

Ex eu aute non proident. Ullamco culpa do ullamco magna. Eu minim anim ut reprehenderit aute nostrud enim veniam cupidatat. Consequat ex fugiat sit duis minim aliquip cupidatat commodo consectetur duis ut do veniam consequat. Laborum do eu enim deserunt labore voluptate. Fugiat nulla dolore non dolor elit dolore aute excepteur pariatur. Non consequat commodo ad nisi sint.

Official source

https://mediaspace.epfl.ch/media/0_dt2vj483

About this result

This page is automatically generated and may contain information that is not correct, complete, up-to-date, or relevant to your search query. The same applies to every other page on this website. Please make sure to verify the information with EPFL's official sources.

Related lectures (31)

Graph Chatbot

Chat with Graph Search

Ask any question about EPFL courses, lectures, exercises, research, news, etc. or try the example questions below.

DISCLAIMER: The Graph Chatbot is not programmed to provide explicit or categorical answers to your questions. Rather, it transforms your questions into API requests that are distributed across the various IT services officially administered by EPFL. Its purpose is solely to collect and recommend relevant references to content that you can explore to help you answer your questions.