Stealthy Attack on Large Language Model based Recommendation

arXiv:2402.14836v1 Announce Type: new
Abstract: Recently, the powerful large language models (LLMs) have been instrumental in propelling the progress of recommender systems (RS). However, while these systems have flourished, their susceptibility to security threats has been largely overlooked. In this work, we reveal that the introduction of LLMs into recommendation models presents new security vulnerabilities due to their emphasis on the textual content of items. We demonstrate that attackers can significantly boost an item's exposure by merely altering its textual …

abstract arxiv cs.ai cs.cl cs.ir introduction language language model language models large language large language model large language models llms progress recommendation recommender systems security systems threats type work