Skip to Content
Hands-On Differential Privacy
book

Hands-On Differential Privacy

by Ethan Cowan, Michael Shoemate, Mayana Pereira
May 2024
Intermediate to advanced
362 pages
8h 47m
English
O'Reilly Media, Inc.
Audio summary available
Content preview from Hands-On Differential Privacy

Appendix C. The Exponential Mechanism Satisfies Bounded Range

An exponential mechanism EMS(·) with quality score S satisfies bounded range with 2ϵ. If S is monotonic over the data, then EMS satisfies bounded range with ϵ.

Proof

When M(·) is the exponential mechanism EMS(·), then given adjacent inputs x and x and outcomes y and y, it suffices to show that:

Pr[M(x)=y]Pr[M(x)=y]Pr[M(x)=y]Pr[M(x)=y]e2ϵ

By the definition of the exponential mechanism, this becomes:

exp(ϵS(x,y)ΔS)exp(ϵS(x,y)ΔS)exp(ϵS(x,y)ΔS)exp(ϵS(x,y)ΔS)

Since ΔS is the sensitivity of the scoring function, we know that |S(x,y)S(x,y)ΔS|1 and |S(x,y)S(x,y)ΔS|1:

exp(ϵ(S(x,y)S(x,y))ΔS)exp(ϵ(S(x,y)S(x,y))ΔS)eϵeϵ=e2ϵ

To demonstrate that EMS satisfies bounded range with ϵ when S is monotonic, consider what this means for adjacent inputs x and x. Monotonicity means that S(a)S(b) when a>b, so there are two possible outcomes:

  • If xx, then S(x,y)S(x,y)0 and S(x,y)S(x,y)0, meaning that:

    exp(ϵ(S(x,y)S(x,y))ΔS)exp(ϵ(S(x,y)S(x,y))ΔS)eϵ·1=eϵ
  • If xx, then S(x,y)S(x,y)0 and S(x,y)S(x,y)0, meaning that:

    exp(ϵ(S(x,y)S(x,y))ΔS)exp(ϵ(S(x,y)S(x,y))ΔS)1·eϵ=eϵ

This concludes the proof.

Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
and much more.

Read now

Unlock full access

More than 5,000 organizations count on O’Reilly

AirBnbBlueOriginElectronic ArtsHomeDepotNasdaqRakutenTata Consultancy Services

QuotationMarkO’Reilly covers everything we've got, with content to help us build a world-class technology community, upgrade the capabilities and competencies of our teams, and improve overall team performance as well as their engagement.
Julian F.
Head of Cybersecurity
QuotationMarkI wanted to learn C and C++, but it didn't click for me until I picked up an O'Reilly book. When I went on the O’Reilly platform, I was astonished to find all the books there, plus live events and sandboxes so you could play around with the technology.
Addison B.
Field Engineer
QuotationMarkI’ve been on the O’Reilly platform for more than eight years. I use a couple of learning platforms, but I'm on O'Reilly more than anybody else. When you're there, you start learning. I'm never disappointed.
Amir M.
Data Platform Tech Lead
QuotationMarkI'm always learning. So when I got on to O'Reilly, I was like a kid in a candy store. There are playlists. There are answers. There's on-demand training. It's worth its weight in gold, in terms of what it allows me to do.
Mark W.
Embedded Software Engineer

You might also like

The Three Traps That Stymie Reinvention

The Three Traps That Stymie Reinvention

Ryan Raffaelli
Exploring GPT-3

Exploring GPT-3

Steve Tingiris
The Human Factor in AI-Based Decision-Making

The Human Factor in AI-Based Decision-Making

Philip Meissner, Christoph Keding

Publisher Resources

ISBN: 9781492097730Errata Page