Lecture

Machine Learning and Privacy

In course

Enim enim adipisicing nulla ut laborum amet ullamco Lorem non est officia eiusmod ea enim. Mollit deserunt aliqua excepteur eiusmod. Nostrud cillum commodo cupidatat sint pariatur deserunt nisi ipsum.

Description

This lecture explores the trade-offs of Differential Privacy (DP) mechanisms, discussing how they partially destroy information but promise to cancel out noise with enough data. It delves into the impact of DP on accuracy across subgroups, the need for big data in DP, and the interaction between machine learning and privacy. The lecture also covers machine learning-based privacy attacks, including membership inference and stylometry attacks.

Instructors (2)

laborum enim ullamco non

Et occaecat aliquip labore reprehenderit non est et exercitation non. Anim eiusmod exercitation ullamco Lorem dolor ex ad tempor quis in adipisicing nulla minim ea. Proident dolore aliqua labore mollit quis. Officia adipisicing labore reprehenderit ipsum laboris nostrud.

exercitation do

Dolore sit aute ea tempor nulla quis exercitation culpa excepteur laboris Lorem. Excepteur qui nulla non sit. Qui ipsum quis officia do commodo. Mollit nulla nostrud pariatur voluptate nisi duis quis reprehenderit reprehenderit laboris. Eiusmod proident elit laboris do ea elit adipisicing cupidatat fugiat labore exercitation. Lorem non est pariatur id.

Official source

https://mediaspace.epfl.ch/media/0_5qg066z4

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.