Privacy in LLM-based Recommendation: Recent Advances and Future Directions

TL;DR

This paper reviews recent progress in addressing privacy concerns in LLM-based recommendation systems, emphasizing attacks, protections, challenges, and future research directions.

Contribution

It provides a comprehensive categorization of privacy attacks and protection mechanisms in LLM-based recommendation, highlighting gaps and proposing future research directions.

Findings

Identification of key privacy attack types

Overview of current protection strategies

Discussion of open challenges and future directions

Abstract

Nowadays, large language models (LLMs) have been integrated with conventional recommendation models to improve recommendation performance. However, while most of the existing works have focused on improving the model performance, the privacy issue has only received comparatively less attention. In this paper, we review recent advancements in privacy within LLM-based recommendation, categorizing them into privacy attacks and protection mechanisms. Additionally, we highlight several challenges and propose future directions for the community to address these critical problems.