WWW 2026 Paper
Title: Inferring Users’ Demographics and Sensitive Interests Using the Topics API
Authors: Athicha Srivirote (Northeastern University), Muhammad Abu Aziz (Northeastern University), Jeffrey Gleason (Northeastern University), Desheng Hu (Department of Informatics, University of Zurich), Christo Wilson (Northeastern University)
Abstract/Summary: In 2019, Google introduced the Privacy Sandbox, a collection of APIs designed to facilitate privacy-preserving online advertising. One of the Sandbox APIs, known as Topics, maps users’ browsing history to a set of commercially-focused topics and then shares the top topics with advertisers. Prior work has shown that the Topics API makes Chrome users vulnerable to cross-context reidentification attacks. In this work, we investigate whether the Topics API can be abused to implement a different privacy attack: accurate inferences of users’ demographics and sensitive interests. To answer this question, we use a real-world dataset of browsing histories—containing over 250,000 unique domains over a span of eight months—to train machine learning models that take topics from the Topics API as input. Of the 19 demographic traits and sensitive interests that we evaluate, we find that all but two show predictive signals. Our findings add to the growing body of evidence that the Topics API is privacy-revealing, not privacy-preserving.