Preserving Privacy and Utility in LLM-Based Product Recommendations

TL;DR

This paper introduces a hybrid privacy-preserving framework for LLM-based recommendation systems that maintains high recommendation quality while significantly enhancing user data privacy, using local de-obfuscation and data separation techniques.

Contribution

It proposes a novel hybrid framework that separates sensitive data, shares only nonsensitive data with the cloud, and reconstructs sensitive recommendations locally, balancing privacy and utility.

Findings

Achieves similar recommendation utility to full data sharing systems.

Improves HR@10 scores over obfuscation-only methods.

Runs efficiently on consumer hardware.

Abstract

Large Language Model (LLM)-based recommendation systems leverage powerful language models to generate personalized suggestions by processing user interactions and preferences. Unlike traditional recommendation systems that rely on structured data and collaborative filtering, LLM-based models process textual and contextual information, often using cloud-based infrastructure. This raises privacy concerns, as user data is transmitted to remote servers, increasing the risk of exposure and reducing control over personal information. To address this, we propose a hybrid privacy-preserving recommendation framework which separates sensitive from nonsensitive data and only shares the latter with the cloud to harness LLM-powered recommendations. To restore lost recommendations related to obfuscated sensitive data, we design a de-obfuscation module that reconstructs sensitive recommendations locally. Experiments on real-world e-commerce datasets show that our framework achieves almost the same recommendation utility with a system which shares all data with an LLM, while preserving privacy to a large extend. Compared to obfuscation-only techniques, our approach improves HR@10 scores and category distribution alignment, offering a better balance between privacy and recommendation quality. Furthermore, our method runs efficiently on consumer-grade hardware, making privacy-aware LLM-based recommendation systems practical for real-world use.