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 which is generated by the service provider itself usually receives less attention and could be accessed within a relatively larger scope of various information seekers or even potential adversaries. In this paper, we investigate the problem of user behavior leakage in the field of recommender systems. We show that the privacy sensitive user past behavior data can be inferred through the modeling of system exposure. In other words, 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. Specifically, we exploit an encoder-decoder structure to construct the attack model and apply different encoding and decoding strategies to verify the attack performance. 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, which is an interesting and important topic for privacy concerns in recommender systems.

A Graph Convolutional Network for Session Recommendation Model Based on Improved Transformer

“…to determine the importance of node v j to node v i in the local session graph [15], we use the value e ij . The activation function used in the calculation is Mish.…”

A Hybrid POI Recommendation System Combining Link Analysis and Collaborative Filtering Based on Various Visiting Behaviors

“…Obtaining informed consent from users for the collection and utilization of their data is also a critical legal obligation. To mitigate the potential privacy risks associated with the user behavior data, it is advisable to consider the adoption of existing privacy preserving recommendation methods such as cryptography-based approaches [37,38] or a two-stage privacy protection mechanism [39]. In addition, the ranks of the location recommendations selected by the user is higher than that of the previous method.…”

Workshop on Learning and Evaluating Recommendations with Impressions (LERI)

“…Recently, a source of information that was previously almost unavailable to the wider research community has emerged with the potential to impact the field in numerous ways: impressions. Impressions [7,15,25,28,37] refer to the items displayed on the screen when a user interacts (or not) with them and are the product of the whole recommendation engine [7,21,22]. Impressions constitute a nuanced and intricate data source that raises novel research questions, opportunities, and challenges.…”