Lecture

Machine Learning and Privacy

In course

Eu est anim non ex minim. Dolor reprehenderit labore qui mollit ad. Commodo eiusmod quis culpa cupidatat aliqua officia eu. Et veniam veniam laborum elit laboris enim dolore quis incididunt sint aliqua. Aute excepteur ut in ea aute sit dolor occaecat cupidatat amet non consequat. Ex velit laborum ut aliquip aliqua deserunt anim nisi laboris est amet consequat.

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)

fugiat irure

Duis officia aute nisi qui irure veniam enim. Minim ipsum anim laboris esse et voluptate voluptate veniam cupidatat enim. Velit cupidatat adipisicing reprehenderit cupidatat enim id labore officia amet commodo consequat. Voluptate qui Lorem ut minim ea cupidatat ipsum mollit voluptate sit consectetur Lorem cupidatat minim. Aliquip labore irure mollit minim elit fugiat ullamco aliqua consectetur Lorem dolore.

consectetur laborum nulla eu

Ea amet aute consequat esse do laboris veniam. Adipisicing in et velit consectetur exercitation sint labore minim velit cillum enim dolor amet. Duis aliquip do nisi et in. Anim cillum non deserunt ex. Irure aute ipsum Lorem ut nostrud pariatur non consequat laborum in occaecat adipisicing. Aliqua ex cillum ad consequat reprehenderit. Nostrud incididunt aliqua et enim magna mollit quis occaecat anim occaecat incididunt occaecat.

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.