arXiv cs.AI· Jiajie He, Xintong Chen, Xinyang Fang, Min-Chun Chen, Yuechun Gu, Wenjin Liu, Keke Chen·· 5 小时前AI 评分36
推荐系统成员推断攻击综述：首个系统性梳理攻击与防御的调研
Membership Inference Attacks on Recommender System: A Survey
AI 导读
研究者在 arXiv 发表首个针对推荐系统成员推断攻击（MIAs）的系统性综述，梳理该领域的设计原理、挑战及攻防进展。MIAs 旨在推断用户的交互记录是否被用于训练目标模型，可直接导致隐私泄露，而传统 MIA 因后验概率不可见而难以直接应用于推荐系统。综述提出统一分类法比较各方法优劣，并指出未来研究方向。
正文 · 原文
Abstract:Recommender systems (RecSys) have been widely applied to various applications, including E-commerce, finance, healthcare, social media and have become increasingly influential in shaping user behavior and decision-making, highlighting their growing impact in various domains. However, recent studies have shown that RecSys are vulnerable to membership inference attacks (MIAs), which aim to infer whether user interaction record was used to train a target model or not. MIAs on RecSys models can directly lead to a privacy breach. For example, via identifying the fact that a purchase record that has been used to train a RecSys associated with a specific user, an attacker can infer that user's special quirks. In recent years, MIAs have been shown to be effective on other ML tasks, e.g., classification models and natural language processing. However, traditional MIAs are ill-suited for RecSys due to the unseen posterior probability. Although MIAs on RecSys form a newly emerging and rapidly growing research area, there has been no systematic survey on this topic yet. In this article, we conduct the first comprehensive survey on RecSys MIAs. This survey offers a comprehensive review of the latest advancements in RecSys MIAs, exploring the design principles, challenges, attack and defense associated with this emerging field. We provide a unified taxonomy that categorizes different RecSys MIAs based on their characterizations and discuss their pros and cons. Based on the limitations and gaps identified in this survey, we point out several promising future research directions to inspire the researchers who wish to follow this area. This survey not only serves as a reference for the research community but also provides a clear description for researchers outside this research domain.
| Comments: | under review in ACM TOIS |
| Subjects: | Information Retrieval (cs.IR); Artificial Intelligence (cs.AI); Cryptography and Security (cs.CR) |
| Cite as: | arXiv:2509.11080 [cs.IR] |
| (or arXiv:2509.11080v5 [cs.IR] for this version) | |
| https://doi.org/10.48550/arXiv.2509.11080 arXiv-issued DOI via DataCite |
Submission history
From: Jiajie He [view email]
[v1]
Sun, 14 Sep 2025 04:06:03 UTC (37 KB)
[v2]
Mon, 27 Oct 2025 05:12:35 UTC (45 KB)
[v3]
Thu, 8 Jan 2026 00:15:19 UTC (1,660 KB)
[v4]
Fri, 11 Sep 2026 02:20:08 UTC (1,111 KB)
[v5]
Thu, 29 Oct 2026 02:29:26 UTC (3,404 KB)
来源：arXiv cs.AI · arxiv.org