CheatAgent: Attacking LLM-Empowered Recommender Systems via LLM Agent-Reference-Cited by-同舟云学术

CheatAgent: Attacking LLM-Empowered Recommender Systems via LLM Agent

Published:2024-08-24 Issue: Volume:41 Page:2284-2295
ISSN:
Container-title:Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining
language:
Short-container-title:

Author:

Ning Liang-bo¹^ORCID,Wang Shijie¹^ORCID,Fan Wenqi²^ORCID,Li Qing¹^ORCID,Xu Xin¹^ORCID,Chen Hao¹^ORCID,Huang Feiran³^ORCID

Affiliation:

1. The Hong Kong Polytechnic University, Hong Kong, China

2. Department of Computing & Department of Management and Marketing, The Hong Kong Polytechnic University, Hong Kong, China

3. Jinan University, Guangzhou, China

Funder

General Research Funds from the Hong Kong Research Grants Council

SHTM Interdisciplinary Large Grant

internal research funds from The Hong Kong Polytechnic University

Research Collaborative Project

National Natural Science Foundation of China

Publisher

ACM

Link

https://dl.acm.org/doi/pdf/10.1145/3637528.3671837

Reference52 articles.

1. Gati V Aher, Rosa I Arriaga, and Adam Tauman Kalai. 2023. Using large language models to simulate multiple humans and replicate human subject studies. In International Conference on Machine Learning. PMLR, 337--371.

2. TALLRec: An Effective and Efficient Tuning Framework to Align Large Language Model with Recommendation

3. Robin Burke, Bamshad Mobasher, and Runa Bhaumik. 2005. Limited knowledge shilling attacks in collaborative filtering systems. In Proceedings of 3rd international workshop on intelligent techniques for web personalization (ITWP 2005), 19th international joint conference on artificial intelligence (IJCAI 2005). 17--24.

4. Knowledge-enhanced Black-box Attacks for Recommendations

5. Adversarial attacks on an oblivious recommender