Puda: Private User Dataset Agent for User-Sovereign and Privacy-Preserving Personalized AI

TL;DR

Puda is a browser-based system that empowers users to control personal data sharing at multiple privacy levels, enabling effective personalized AI services while preserving user sovereignty and privacy.

Contribution

It introduces a user-sovereign architecture for data aggregation and client-side management, balancing personalization and privacy in AI services.

Findings

Predefined Category Subsets achieve 97.2% of full data personalization performance.

Puda enables multi-granularity data management for privacy-preserving personalization.

Effective privacy-personalization trade-off mitigation demonstrated in travel planning task.

Abstract

Personal data centralization among dominant platform providers including search engines, social networking services, and e-commerce has created siloed ecosystems that restrict user sovereignty, thereby impeding data use across services. Meanwhile, the rapid proliferation of Large Language Model (LLM)-based agents has intensified demand for highly personalized services that require the dynamic provision of diverse personal data. This presents a significant challenge: balancing the utilization of such data with privacy protection. To address this challenge, we propose Puda (Private User Dataset Agent), a user-sovereign architecture that aggregates data across services and enables client-side management. Puda allows users to control data sharing at three privacy levels: (i) Detailed Browsing History, (ii) Extracted Keywords, and (iii) Predefined Category Subsets. We implemented Puda as a browser-based system that serves as a common platform across diverse services and evaluated it through a personalized travel planning task. Our results show that providing Predefined Category Subsets achieves 97.2% of the personalization performance (evaluated via an LLM-as-a-Judge framework across three criteria) obtained when sharing Detailed Browsing History. These findings demonstrate that Puda enables effective multi-granularity management, offering practical choices to mitigate the privacy-personalization trade-off. Overall, Puda provides an AI-native foundation for user sovereignty, empowering users to safely leverage the full potential of personalized AI.