Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Differentially Private Ad Conversion Measurement

John Delaney, Badih Ghazi, Charlie Harrison, Christina Ilvento, Ravi Kumar, Pasin Manurangsi, Martin Pal, Karthik Prabhakar, Mariana Raykova

TL;DR

This work defines the notion of an operationally valid configuration of the attribution rule, DP adjacency relation, contribution bounding scope and enforcement point, and provides a complete characterization, which uncovers a delicate interplay between attribution and privacy.

Abstract

In this work, we study ad conversion measurement, a central functionality in digital advertising, where an advertiser seeks to estimate advertiser website (or mobile app) conversions attributed to ad impressions that users have interacted with on various publisher websites (or mobile apps). Using differential privacy (DP), a notion that has gained in popularity due to its strong mathematical guarantees, we develop a formal framework for private ad conversion measurement. In particular, we define the notion of an operationally valid configuration of the attribution rule, DP adjacency relation, contribution bounding scope and enforcement point. We then provide, for the set of configurations that most commonly arises in practice, a complete characterization, which uncovers a delicate interplay between attribution and privacy.

Differentially Private Ad Conversion Measurement

TL;DR

This work defines the notion of an operationally valid configuration of the attribution rule, DP adjacency relation, contribution bounding scope and enforcement point, and provides a complete characterization, which uncovers a delicate interplay between attribution and privacy.

Abstract

In this work, we study ad conversion measurement, a central functionality in digital advertising, where an advertiser seeks to estimate advertiser website (or mobile app) conversions attributed to ad impressions that users have interacted with on various publisher websites (or mobile apps). Using differential privacy (DP), a notion that has gained in popularity due to its strong mathematical guarantees, we develop a formal framework for private ad conversion measurement. In particular, we define the notion of an operationally valid configuration of the attribution rule, DP adjacency relation, contribution bounding scope and enforcement point. We then provide, for the set of configurations that most commonly arises in practice, a complete characterization, which uncovers a delicate interplay between attribution and privacy.
Paper Structure (66 sections, 17 theorems, 2 equations, 3 figures, 5 tables, 2 algorithms)

This paper contains 66 sections, 17 theorems, 2 equations, 3 figures, 5 tables, 2 algorithms.

Table of Contents

  1. Introduction
  2. Motivation, Setup & Contributions
  3. Ad Conversion Measurement System
  4. Basic Definitions.
  5. Attribution Rule
  6. Privacy Model
  7. Threat Model
  8. Differential Privacy Ingredients
  9. Adjacency Relation
  10. Contribution Bounding Scope
  11. Contribution Bound Enforcement
  12. Valid Configurations
  13. Our Contributions
  14. Classification
  15. Example of an Invalid Configuration
  16. ...and 51 more sections

Key Result

Lemma 1

If the attribution system is instantiated with a $C_0$-valid configuration and each coordinate of the noise $Z$ is sampled according to the Laplace distribution with scale parameter $C_0 \cdot r \cdot \Delta(f) / \varepsilon$, then the conversion measurement system is $\varepsilon$-DP.

Figures (3)

  • Figure 1: Example Attribution Path. In this case, a user interacts with four ad impressions from the same advertiser, but on four different publishers. The third of these interactions is a view, whereas the others are clicks. For simplicity, we assume that the four impressions and the subsequent conversion occur at equally spaced times.
  • Figure 2: Attribution Path for Multiple Publishers and Advertisers. In this example, the user interacts with ads on two publishers, and converts on the two corresponding advertiser websites.
  • Figure 3: Illustration of a (DP) Conversion Measurement System. Each coordinate of the noise $Z$ is drawn from the Laplace distribution with an appropriate scale (see \ref{['lem:main-dp']}). We note that the attribution system can include a contribution bound enforcement component (this is the case in Algorithms \ref{['alg:post-attr']} and \ref{['alg:pre-attr']}).

Theorems & Definitions (28)

  • Example 1
  • Remark 1
  • Remark 2: Intuitive Interpretation of the Different Adjacency Relations
  • Remark 3: Time Dimension in Adjacency Relations
  • Definition 1: Differential Privacy dwork06calibrating
  • Definition 2: Attributed Dataset
  • Definition 3: Sensitivity of $f$
  • Definition 4: Valid Configurations
  • Lemma 1
  • Remark 4
  • ...and 18 more