Stronger Privacy for Federated Collaborative Filtering with Implicit Feedback

05/09/2021
by   Lorenzo Minto, et al.
0

Recommender systems are commonly trained on centrally collected user interaction data like views or clicks. This practice however raises serious privacy concerns regarding the recommender's collection and handling of potentially sensitive data. Several privacy-aware recommender systems have been proposed in recent literature, but comparatively little attention has been given to systems at the intersection of implicit feedback and privacy. To address this shortcoming, we propose a practical federated recommender system for implicit data under user-level local differential privacy (LDP). The privacy-utility trade-off is controlled by parameters ϵ and k, regulating the per-update privacy budget and the number of ϵ-LDP gradient updates sent by each user respectively. To further protect the user's privacy, we introduce a proxy network to reduce the fingerprinting surface by anonymizing and shuffling the reports before forwarding them to the recommender. We empirically demonstrate the effectiveness of our framework on the MovieLens dataset, achieving up to Hit Ratio with K=10 (HR@10) 0.68 on 50k users with 5k items. Even on the full dataset, we show that it is possible to achieve reasonable utility with HR@10>0.5 without compromising user privacy.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
04/17/2023

DRIFT: A Federated Recommender System with Implicit Feedback on the Items

Nowadays there are more and more items available online, this makes it h...
research
09/14/2021

Position Paper on Simulating Privacy Dynamics in Recommender Systems

In this position paper, we discuss the merits of simulating privacy dyna...
research
07/14/2021

Self-Determined Reciprocal Recommender System with Strong Privacy Guarantees

Recommender systems are widely used. Usually, recommender systems are ba...
research
04/13/2018

The Users' Perspective on the Privacy-Utility Trade-offs in Health Recommender Systems

Privacy is a major good for users of personalized services such as recom...
research
05/04/2023

The Application of Affective Measures in Text-based Emotion Aware Recommender Systems

This paper presents an innovative approach to address the problems resea...
research
05/12/2023

Eye Tracking as a Source of Implicit Feedback in Recommender Systems: A Preliminary Analysis

Eye tracking in recommender systems can provide an additional source of ...
research
05/14/2023

Manipulating Visually-aware Federated Recommender Systems and Its Countermeasures

Federated recommender systems (FedRecs) have been widely explored recent...

Please sign up or login with your details

Forgot password? Click here to reset