AdFL: In-Browser Federated Learning for Online Advertisement

2026-02-06

AI Summary

This work proposes AdFL, the first plug-in-free federated learning framework for online advertising that operates entirely within standard browser APIs—such as Fetch and IndexedDB—while complying with privacy regulations like the GDPR. AdFL trains personalized user preference models locally on client-side behavioral data, including ad visibility, click-through rates, and dwell time, without uploading raw data to third parties. Global model aggregation is coordinated through publisher servers, and differential privacy is integrated to further enhance user confidentiality. Evaluated on a real-world website with approximately 40,000 daily visitors, the system incurs only a few milliseconds of computational overhead per user and achieves an AUC of 92.59% for ad visibility prediction. The incorporation of differential privacy results in only marginal performance degradation, demonstrating the framework’s practicality and efficiency.

Technology Category

• Machine Learning: Privacy
• Application Domains: Web
• Multiagent Systems: Adversarial Agents

Application Category

• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization
• Responsible Web: Consent frameworks and practices on the web
• Search and Retrieval-Augmented AI: Ad search and search for Web retail

Abstract

Since most countries are coming up with online privacy regulations, such as GDPR in the EU, online publishers need to find a balance between revenue from targeted advertisement and user privacy. One way to be able to still show targeted ads, based on user personal and behavioral information, is to employ Federated Learning (FL), which performs distributed learning across users without sharing user raw data with other stakeholders in the publishing ecosystem. This paper presents AdFL, an FL framework that works in the browsers to learn user ad preferences. These preferences are aggregated in a global FL model, which is then used in the browsers to show more relevant ads to users. AdFL can work with any model that uses features available in the browser such as ad viewability, ad click-through, user dwell time on pages, and page content. The AdFL server runs at the publisher and coordinates the learning process for the users who browse pages on the publisher's website. The AdFL prototype does not require the client to install any software, as it is built utilizing standard APIs available on most modern browsers. We built a proof-of-concept model for ad viewability prediction that runs on top of AdFL. We tested AdFL and the model with two non-overlapping datasets from a website with 40K visitors per day. The experiments demonstrate AdFL's feasibility to capture the training information in the browser in a few milliseconds, show that the ad viewability prediction achieves up to 92.59% AUC, and indicate that utilizing differential privacy (DP) to safeguard local model parameters yields adequate performance, with only modest declines in comparison to the non-DP variant.

Problem

• Federated Learning
• Online Advertisement
• User Privacy
• GDPR
• Targeted Advertising

Innovation

• Federated Learning
• In-Browser Learning
• Differential Privacy
• Online Advertising
• Privacy-Preserving AI