Private Ad Modeling with DP-SGD

TL;DR

This paper applies differential privacy stochastic gradient descent (DP-SGD) to ad modeling tasks, demonstrating its effectiveness in balancing privacy and utility on real-world datasets with high class imbalance.

Contribution

First empirical evaluation of DP-SGD on ad data, showing it can preserve privacy while maintaining utility in click-through and conversion rate predictions.

Findings

DP-SGD achieves privacy-utility trade-off in ad modeling

Effective on datasets with high class imbalance

Demonstrates practical applicability of DP-SGD in advertising

Abstract

A well-known algorithm in privacy-preserving ML is differentially private stochastic gradient descent (DP-SGD). While this algorithm has been evaluated on text and image data, it has not been previously applied to ads data, which are notorious for their high class imbalance and sparse gradient updates. In this work we apply DP-SGD to several ad modeling tasks including predicting click-through rates, conversion rates, and number of conversion events, and evaluate their privacy-utility trade-off on real-world datasets. Our work is the first to empirically demonstrate that DP-SGD can provide both privacy and utility for ad modeling tasks.