ID-Free Not Risk-Free: LLM-Powered Agents Unveil Risks in ID-Free Recommender Systems
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916708220928000 |
|---|---|
| author | Wang, Zongwei Gao, Min Yu, Junliang Gao, Xinyi Nguyen, Quoc Viet Hung Sadiq, Shazia Yin, Hongzhi |
| author_facet | Wang, Zongwei Gao, Min Yu, Junliang Gao, Xinyi Nguyen, Quoc Viet Hung Sadiq, Shazia Yin, Hongzhi |
| contents | Recent advances in ID-free recommender systems have attracted significant attention for effectively addressing the cold start problem. However, their vulnerability to malicious attacks remains largely unexplored. In this paper, we unveil a critical yet overlooked risk: LLM-powered agents can be strategically deployed to attack ID-free recommenders, stealthily promoting low-quality items in black-box settings. This attack exploits a novel rewriting-based deception strategy, where malicious agents synthesize deceptive textual descriptions by simulating the characteristics of popular items. To achieve this, the attack mechanism integrates two primary components: (1) a popularity extraction component that captures essential characteristics of popular items and (2) a multi-agent collaboration mechanism that enables iterative refinement of promotional textual descriptions through independent thinking and team discussion. To counter this risk, we further introduce a detection method to identify suspicious text generated by our discovered attack. By unveiling this risk, our work aims to underscore the urgent need to enhance the security of ID-free recommender systems. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_11690 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | ID-Free Not Risk-Free: LLM-Powered Agents Unveil Risks in ID-Free Recommender Systems Wang, Zongwei Gao, Min Yu, Junliang Gao, Xinyi Nguyen, Quoc Viet Hung Sadiq, Shazia Yin, Hongzhi Information Retrieval Recent advances in ID-free recommender systems have attracted significant attention for effectively addressing the cold start problem. However, their vulnerability to malicious attacks remains largely unexplored. In this paper, we unveil a critical yet overlooked risk: LLM-powered agents can be strategically deployed to attack ID-free recommenders, stealthily promoting low-quality items in black-box settings. This attack exploits a novel rewriting-based deception strategy, where malicious agents synthesize deceptive textual descriptions by simulating the characteristics of popular items. To achieve this, the attack mechanism integrates two primary components: (1) a popularity extraction component that captures essential characteristics of popular items and (2) a multi-agent collaboration mechanism that enables iterative refinement of promotional textual descriptions through independent thinking and team discussion. To counter this risk, we further introduce a detection method to identify suspicious text generated by our discovered attack. By unveiling this risk, our work aims to underscore the urgent need to enhance the security of ID-free recommender systems. |
| title | ID-Free Not Risk-Free: LLM-Powered Agents Unveil Risks in ID-Free Recommender Systems |
| topic | Information Retrieval |
| url | https://arxiv.org/abs/2409.11690 |