SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2402.14836 · ACL · 2024

Stealthy Attack on Large Language Model based Recommendation

Qiang Liu, Liang Wang, Shu Wu, Guibing Guo, Jinghao Zhang, Yuting Liu

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

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 content during the testing phase, without requiring direct interference with the model's training process. Additionally, the attack is notably stealthy, as it does not affect the overall recommendation performance and the modifications to the text are subtle, making it difficult for users and platforms to detect. Our comprehensive experiments across four mainstream LLM-based recommendation models demonstrate the superior efficacy and stealthiness of our approach. Our work unveils a significant security gap in LLM-based recommendation systems and paves the way for future research on protecting these systems. 1

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2402.14836")
get_code_for_paper("2402.14836")
have("2402.14836")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2402.14836.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2402.14836.svg)](https://syntology.ai/paper/2402.14836)

Connect an agent — have() is free.