University of Cambridge > Talks.cam > Engineering Safe AI > The Algorithmic Foundations of Differential Privacy (Chapters 1 and 2)

The Algorithmic Foundations of Differential Privacy (Chapters 1 and 2)

Add to your list(s) Download to your calendar using vCal

If you have a question about this talk, please contact Adrià Garriga Alonso.

Link: http://www.cis.upenn.edu/~aaroth/privacybook.html (DO NOT MINDLESSLY PRINT , we will only be going over a tenth (Chapters 1 and 2) of this document so you don’t need to print the rest unless you are extraordinarily keen)

Abstract: “A major imminent concern in the deployment of AI and the collection of data regards the privacy implications. In this week’s reading group we will learn the definition of Differential Privacy, why it is useful, what it is/guarantees, what it isn’t/doesn’t and a little about how much is and is not possible within the constraint that it provides.

The problem of privacy-preserving data analysis has a long history spanning multiple disciplines. As electronic data about individuals becomes increasingly detailed, and as technology enables ever more powerful collection and curation of these data, the need increases for a robust, meaningful, and mathematically rigorous definition of privacy, together with a computationally rich class of algorithms that satisfy this definition. Differential Privacy is such a definition.”

At 17:00, we will start reading the paper, mostly individually. At 17:30, the discussion leader will start going through the paper, making sure everyone understands, and encouraging discussion about its contents and implications.

Even if you think you cannot contribute to the conversation, you should give it a try. Last year we had several people from non-computer-y backgrounds, and others who hadn’t thought about alignment before, that ended up being essential. If you have already read the paper in your own time you can come in time for the discussion.

A basic understanding of machine learning is helpful, but detailed knowledge of the latest techniques is not required. Each session will have a brief recap of immediate necessary knowledge. The goal of this series is to get people to know more about the existing work in AI research, and eventually contribute to the field.

Invite your friends to join the talks.cam page (https://talks.cam.ac.uk/show/index/80932) or the Facebook group (https://www.facebook.com/groups/1070763633063871). Details about the next meeting, the week’s topic and other events will be advertised in these places as well.

This talk is part of the Engineering Safe AI series.

Tell a friend about this talk:

This talk is included in these lists:

Note that ex-directory lists are not shown.

 

© 2006-2024 Talks.cam, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity