Membership Inference Attacks Against Recommender Systems

by   Minxing Zhang, et al.

Recently, recommender systems have achieved promising performances and become one of the most widely used web applications. However, recommender systems are often trained on highly sensitive user data, thus potential data leakage from recommender systems may lead to severe privacy problems. In this paper, we make the first attempt on quantifying the privacy leakage of recommender systems through the lens of membership inference. In contrast with traditional membership inference against machine learning classifiers, our attack faces two main differences. First, our attack is on the user-level but not on the data sample-level. Second, the adversary can only observe the ordered recommended items from a recommender system instead of prediction results in the form of posterior probabilities. To address the above challenges, we propose a novel method by representing users from relevant items. Moreover, a shadow recommender is established to derive the labeled training data for training the attack model. Extensive experimental results show that our attack framework achieves a strong performance. In addition, we design a defense mechanism to effectively mitigate the membership inference threat of recommender systems.


page 7

page 9

page 10

page 12

page 17


Debiasing Learning for Membership Inference Attacks Against Recommender Systems

Learned recommender systems may inadvertently leak information about the...

Membership Inference Attacks Against Latent Factor Model

The advent of the information age has led to the problems of information...

Privacy-Adversarial User Representations in Recommender Systems

Latent factor models for recommender systems represent users and items a...

Interaction-level Membership Inference Attack Against Federated Recommender Systems

The marriage of federated learning and recommender system (FedRec) has b...

Defending Substitution-Based Profile Pollution Attacks on Sequential Recommenders

While sequential recommender systems achieve significant improvements on...

RecAD: Towards A Unified Library for Recommender Attack and Defense

In recent years, recommender systems have become a ubiquitous part of ou...

Please sign up or login with your details

Forgot password? Click here to reset