AI Insight
This survey paper provides the first comprehensive review of membership inference attacks (MIAs) on recommender systems, which attempt to determine whether a specific user's interaction data was used to train a recommendation model. The authors present a unified taxonomy categorizing different attack methods and defenses, while identifying that traditional MIAs designed for classification tasks are poorly suited for recommender systems due to differences in model outputs. The paper highlights how successful attacks can reveal sensitive information about users' preferences and behaviors, constituting significant privacy breaches.
Why it matters
As recommender systems increasingly influence user behavior across e-commerce, healthcare, finance, and social media platforms, understanding their privacy vulnerabilities is critical. These attacks could expose sensitive personal information, such as medical conditions or purchasing habits, making effective defenses essential for protecting user privacy in widely deployed systems.
Understand the Science
⚠️ Preprint – Noch nicht peer-reviewed
Dieser Artikel wurde noch nicht von unabhängigen Experten begutachtet. Die Ergebnisse sind vorläufig und sollten mit Vorsicht interpretiert werden.
-cross
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.
Source: Membership Inference Attacks on Recommender System: A Survey