LLM-Powered Text Simulation Attack Against ID-Free Recommender Systems

Abstract

The ID-free recommendation paradigm has been proposed to address the limitation that traditional recommender systems struggle to model cold-start users or items with new IDs. Despite its effectiveness, this study uncovers that ID-free recommender systems are vulnerable to the proposed Text Simulation attack (TextSimu) which aims to promote specific target items. As a novel type of text poisoning attack, TextSimu exploits large language models (LLM) to alter the textual information of target items by simulating the characteristics of popular items. It operates effectively in both black-box and white-box settings, utilizing two key components: a unified popularity extraction module, which captures the essential characteristics of popular items, and an N-persona consistency simulation strategy, which creates multiple personas to collaboratively synthesize refined promotional textual descriptions for target items by simulating the popular items. To withstand TextSimu-like attacks, we further explore the detection approach for identifying LLM-generated promotional text. Extensive experiments conducted on three datasets demonstrate that TextSimu poses a more significant threat than existing poisoning attacks, while our defense method can detect malicious text of target items generated by TextSimu. By identifying the vulnerability, we aim to advance the development of more robust ID-free recommender systems.