On the User Behavior Leakage from Recommender System Exposure

by   Xin Xin, et al.

Modern recommender systems are trained to predict users potential future interactions from users historical behavior data. During the interaction process, despite the data coming from the user side recommender systems also generate exposure data to provide users with personalized recommendation slates. Compared with the sparse user behavior data, the system exposure data is much larger in volume since only very few exposed items would be clicked by the user. Besides, the users historical behavior data is privacy sensitive and is commonly protected with careful access authorization. However, the large volume of recommender exposure data usually receives less attention and could be accessed within a relatively larger scope of various information seekers. In this paper, we investigate the problem of user behavior leakage in recommender systems. We show that the privacy sensitive user past behavior data can be inferred through the modeling of system exposure. Besides, one can infer which items the user have clicked just from the observation of current system exposure for this user. Given the fact that system exposure data could be widely accessed from a relatively larger scope, we believe that the user past behavior privacy has a high risk of leakage in recommender systems. More precisely, we conduct an attack model whose input is the current recommended item slate (i.e., system exposure) for the user while the output is the user's historical behavior. Experimental results on two real-world datasets indicate a great danger of user behavior leakage. To address the risk, we propose a two-stage privacy-protection mechanism which firstly selects a subset of items from the exposure slate and then replaces the selected items with uniform or popularity-based exposure. Experimental evaluation reveals a trade-off effect between the recommendation accuracy and the privacy disclosure risk.


page 3

page 18

page 19

page 22


Adversarial Counterfactual Learning and Evaluation for Recommender System

The feedback data of recommender systems are often subject to what was e...

Privacy-Adversarial User Representations in Recommender Systems

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

Why People Skip Music? On Predicting Music Skips using Deep Reinforcement Learning

Music recommender systems are an integral part of our daily life. Recent...

Membership Inference Attacks Against Latent Factor Model

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

Discovery Dynamics: Leveraging Repeated Exposure for User and Music Characterization

Repetition in music consumption is a common phenomenon. It is notably mo...

Are Big Recommendation Models Fair to Cold Users?

Big models are widely used by online recommender systems to boost recomm...

Please sign up or login with your details

Forgot password? Click here to reset