This repository explores applying Chrome's Privacy Sandbox concepts to Real-Time Bidding (RTB) to enhance user privacy. It targets advertising exchanges and bidders seeking to implement stronger privacy protections while maintaining RTB's effectiveness for audience reach and monetization. The project facilitates experiments with new RTB interfaces and data signals.

How It Works

The project investigates adapting Privacy Sandbox proposals like TURTLEDOVE and Federated Learning of Cohorts (FLoC) to the RTB ecosystem. It proposes changes to the RTB interface to support aggregated audience targeting, enabling advertisers to reach groups of users rather than individuals. It also explores using sandboxing for ad selection logic and concepts like Privacy Budgets to reduce reliance on high-entropy identifiers like IP addresses.

Highlighted Details

• Explores TURTLEDOVE simulation to evaluate micro-targeting protections.
• Investigates Frequency Capping and Structured User Agent/Geolocation proposals.
• Examines exchange-assisted invalid traffic filtering and server trust models.
• Considers Trusted Execution Environments and Sandboxes for privacy-preserving ad selection.

Maintenance & Community

This is a Google project focused on research and experimentation in the advertising technology space. Specific community channels or active development contributors are not detailed in the README.

Licensing & Compatibility

The repository's license is not specified in the provided README. Compatibility for commercial use or closed-source linking would depend on the eventual licensing terms.

Limitations & Caveats

The README outlines conceptual discussions and experimental proposals rather than a production-ready system. The project is in an exploratory phase, and the viability and implementation details of these privacy-enhancing techniques within RTB are subject to ongoing evaluation and industry input.