Next Meetup

Differential Privacy
"Differential Privacy", by Cynthia Dwork (2006). Presented by Mike Mull. ABSTRACT: In 1977 Dalenius articulated a desideratum for statistical databases: nothing about an individual should be learnable from the database that cannot be learned without access to the database. We give a general impossibility result showing that a formalization of Dalenius’ goal along the lines of semantic security cannot be achieved. Contrary to intuition, a variant of the result threatens the privacy even of someone not in the database. This state of affairs suggests a new measure, differential privacy, which, intuitively, captures the increased risk to one's privacy incurred by participating in a database. The techniques developed in a sequence of papers [8, 13, 3], culminating in those described in [12], can achieve any desired level of privacy under this measure. In many cases, extremely accurate information about the database can be provided while simultaneously ensuring very high levels of privacy. INTRODUCTORY MATERIALS: Here's a video of Cynthia Dwork herself that serves as a great introduction to the topic of Differential Privacy: This blog post also introduces the topic well: and this follow-up goes into more detail if you want it: SOME ADVICE ON READING THE PAPER: The paper is oddly organized. For example, Theorem 1 references Assumption 3, which isn't introduced until two pages later. The title topic isn't formally introduced until Section 4. If you just want to get familiar with the paper before the meet-up my advice would be the following plan: - Read sections 1 and 2. - Read the beginning of section 3 to learn some of the terminology - Skip the remainder of section 3, which is Theorem 1 and its proof. I will cover it in the presentation but it is not essential to the mechanics of differential privacy. - Read section 4, which introduces the formal definition of differential privacy - (Extra credit) Read the introduction to section 5, and section 5.1. ADMINISTRIVIA: Street parking on 6th, 7th & 8th Avenues north of B Street is usually easy at that hour. Meters nearby are free after 6. Read signage before you park on A street. If you're interested in presenting a paper please fill out this form ( or talk to us in person at the meetup.

güdTECH Offices

600 B Street, Ste 2120 · San Diego, CA

1 comment

Upcoming Meetups

Past Meetups (21)

What we're about

This meetup is a chapter of Papers We Love ( The general format is that once a month one member will present one computer science paper using e.g. speech, slides, demonstration. Attendees are encouraged, but not required, to read and digest the paper in advance of the meeting.

One goal is to help bridge the gap between San Diego industry and academics: membership of both types are very welcome. Another goal is to dive deep into interesting programming topics: new and old (but still relevant).

We require adherence to a code of conduct:

If you'd like to present a paper please fill out this form: (

If you don't know what paper to present, check out our recommended papers: (

If you want to see a paper presented add it to the same list: (

If you are new to reading papers, please see "How to Read a Paper":
And these other resources:




speaker instructions:



Members (399)

Photos (14)