PrivacyGo: Privacy-Preserving Ad Measurement with Multidimensional Intersection

2025-06-25

AI Summary

This paper addresses privacy-preserving cross-platform ad attribution measurement in multi-identifier environments. Methodologically, it proposes a secure and practical user identity matching framework that integrates reverse oblivious pseudorandom functions (rOPRFs), blind key rotation, and differential privacy perturbation. This combination enables unlinkable intersection computation across identifiers while concealing the intersection cardinality to resist membership inference attacks. Unlike conventional OPRF-based approaches, the framework supports efficient key updates and scalable deployment. Experiments on billion-scale datasets demonstrate low latency and high accuracy, alongside strong privacy guarantees—formally satisfying ε-differential privacy—while maintaining industrial usability. The solution is directly applicable to real-world secure advertising conversion tracking.

Technology Category

• Machine Learning: Privacy
• Multiagent Systems: Adversarial Agents
• Computer Vision: Adversarial Attacks & Robustness

Application Category

• Security and Privacy: Large-scale security measurements
• User Modeling, Personalization and Recommendation: User privacy protection in personalized systems
• Responsible Web: Data and user privacy-enhancing technologies for the Web

Abstract

This paper tackles the challenging and practical problem of multi-identifier private user profile matching for privacy-preserving ad measurement, a cornerstone of modern advertising analytics. We introduce a comprehensive cryptographic framework leveraging reversed Oblivious Pseudorandom Functions (OPRF) and novel blind key rotation techniques to support secure matching across multiple identifiers. Our design prevents cross-identifier linkages and includes a differentially private mechanism to obfuscate intersection sizes, mitigating risks such as membership inference attacks. We present a concrete construction of our protocol that achieves both strong privacy guarantees and high efficiency. It scales to large datasets, offering a practical and scalable solution for privacy-centric applications like secure ad conversion tracking. By combining rigorous cryptographic principles with differential privacy, our work addresses a critical need in the advertising industry, setting a new standard for privacy-preserving ad measurement frameworks.

Problem

• Multi-identifier private user profile matching for ad measurement
• Preventing cross-identifier linkages in ad analytics
• Ensuring privacy and efficiency in ad conversion tracking

Innovation

• Uses reversed OPRF for secure matching
• Employs blind key rotation techniques
• Integrates differential privacy for obfuscation