Membership Inference Attacks on LLM-based Recommender Systems
Year: 2026
Type: article
Abstract: Large language models (LLMs) based recommender systems (RecSys) can adapt flexibly across different domains. It uses in-context learning (ICL), i.e., prompts, including sensitive historical user-specific item interactions, to customize the recommendation functions. However, no study has examined whether such private information may be exposed by novel privacy attacks. We design several membership inference attacks (MIAs): Similarity, Memorization, Inquiry, and Poisoning attacks, aiming to reveal whether system prompts include victims’ historical interactions. We have carefully evaluated them on the latest open-source LLMs and three well-known RecSys datasets. The results confirm that the MIA threat to LLM RecSys is realistic, and that existing promptbased defense methods may be insufficient to protect against these attacks.
DOI: 10.13016/m2398j-xiak
Authors: He, Jiajie, Chen, Min-Chun, Chen, Xintong, Fang, Xinyang, Gu, Yuechun, Chen, Keke
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W7128804958
FWCI:
Cites:
Cited by:
Related to: