Private-by-Design Advertising Meets the Real World

Abstract

There are a number of designs for an online advertising system that allow for behavioral targeting without revealing user online behavior or user interest profiles to the ad network. However, none of the proposed designs have been deployed in real-life settings. We present an effort to fill this gap by building and evaluating a fully functional prototype of a practical privacy-preserving ad system at a reasonably large scale. With more than 13K opted-in users, our system was in operation for over two months serving an average of 4800 active users daily. During the last month alone, we registered 790K ad views, 417 clicks, and even a small number of product purchases. In addition, our prototype is equipped with a differentially private data collection mechanism, which we used as the primary means for gathering experimental data. The data we collected show, for example, that our system obtained click-through rates comparable with those for Google display ads. In this paper, we describe our first-hand experience and lessons learned in running the first fully operational "private-by-design" behavioral advertising and analytics system.

Evade Deep Image Retrieval by Stashing Private Images in the Hash Space

“…Previous efforts of preserving privacy online mainly focus on web analytics [14,15], mobile advertising [16,17] and behavioral tracking [38,39]. To balance privacy and utility, a popular approach is through differential privacy that introduces noise to answers so the service provider cannot detect the presence or absence of a user.…”

“…Further, users' awareness of their privacy remains quite subjective towards latent, but sensitive information in their images. The resourceful visual content can be exploited in bewildering ways to learn private information such as family member, location, income, personal interest or even sexual orientation for accurate contextual advertising [14][15][16][17] or spear phishing [18]. For example, Facebook has patented a new application of predicting household demographics based on image data [19].…”

Threats to Online Advertising and Countermeasures

“…The scheme consists of two modules building user profile with privacy and rendering ads into publisher pages when the participated publishers' websites are visited. However, according to Reference [69], none of these designs have been implemented and deployed in the real world. The authors of Reference [69] attempt to remedy this situation by building and evaluating a fully functional prototype of a practical privacy-preserving ad system at a reasonably large scale and deploying it.…”

“…However, according to Reference [69], none of these designs have been implemented and deployed in the real world. The authors of Reference [69] attempt to remedy this situation by building and evaluating a fully functional prototype of a practical privacy-preserving ad system at a reasonably large scale and deploying it. The authors claim to have more than 13K opted-in users.…”

Protecting Privacy in Shared Photos via Adversarial Examples Based Stealth

“…Another shocking news is that a new crop of digital marketing firms emerge. They aim at searching, scanning, storing, and repurposing images uploaded to popular photo-sharing sites, to facilitate marketers to send targeted ads [6,7] or conduct market research [8]. These behaviors of large-scale continuous accessing users' private information will, no doubt, make the photo owners very disturbed.…”