On the User Behavior Leakage from Recommender System Exposure

Abstract

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.

arXiv commentSubmitted to the Special Section on Trustworthy Recommendation and Search of ACM TOIS on May 31, 2022 and accepted on October 4

References in corpus (9)

• Neural Graph Collaborative Filtering
• Federated Collaborative Filtering for Privacy-Preserving Personalized Recommendation System
• Reinforced Negative Sampling over Knowledge Graph for Recommendation
• Degenerate Feedback Loops in Recommender Systems
• General factorization framework for context-aware recommendations
• Privacy-Aware Recommendation with Private-Attribute Protection using Adversarial Learning
• A Payload Optimization Method for Federated Recommender Systems
• Fast-adapting and Privacy-preserving Federated Recommender System
• Comprehensive Privacy Analysis on Federated Recommender System against Attribute Inference Attacks

Cited by in corpus (5)

• Multi-queue Momentum Contrast for Microvideo-Product Retrieval
• Debiasing Sequential Recommenders through Distributionally Robust Optimization over System Exposure
• Making Alice Appear Like Bob: A Probabilistic Preference Obfuscation Method For Implicit Feedback Recommendation Models
• Impression-Aware Recommender Systems
• Unlearning Inversion Attacks for Graph Neural Networks