Recommender Systems with Condensed Local Differential Privacy

2020 ◽  
pp. 355-365
Author(s):  
Ao Liu ◽  
Yanqing Yao ◽  
Xianfu Cheng
Keyword(s):  
Recommender Systems ◽  
Differential Privacy

A differential privacy framework for matrix factorization recommender systems

2016 ◽  
Vol 26 (5) ◽  
pp. 425-458 ◽  
Author(s):  
Arik Friedman ◽  
Shlomo Berkovsky ◽  
Mohamed Ali Kaafar
Keyword(s):  
Recommender Systems ◽  
Matrix Factorization ◽  
Differential Privacy

scholarly journals A Differential Privacy Framework for Collaborative Filtering

2019 ◽  
Vol 2019 ◽  
pp. 1-11 ◽  
Author(s):  
Jing Yang ◽  
Xiaoye Li ◽  
Zhenlong Sun ◽  
Jianpei Zhang
Keyword(s):  
Collaborative Filtering ◽  
Recommender Systems ◽  
Perturbation Methods ◽  
Differential Privacy ◽  
Feasible Solution ◽  
Experimental Results ◽  
Input Method ◽  
Recommendation Algorithms ◽  
Inference Attacks ◽  
Privacy Issues

Focusing on the privacy issues in recommender systems, we propose a framework containing two perturbation methods for differentially private collaborative filtering to prevent the threat of inference attacks against users. To conceal individual ratings and provide valuable predictions, we consider some representative algorithms to calculate the predicted scores and provide specific solutions for adding Laplace noise. The DPI (Differentially Private Input) method perturbs the original ratings, which can be followed by any recommendation algorithms. By contrast, the DPM (Differentially Private Manner) method is based on the original ratings, which perturbs the measurements during implementation of the algorithms and releases the predicted scores. The experimental results showed that both methods can provide valuable prediction results while guaranteeing DP, which suggests it is a feasible solution and can be competent to make private recommendations.

scholarly journals Differential Privacy and Bayesian for Context-Aware Recommender Systems

2021 ◽  
Vol 15 (4) ◽  
pp. 0-0
Keyword(s):  
Bayesian Network ◽  
Recommender Systems ◽  
Privacy Protection ◽  
Recommendation System ◽  
Differential Privacy ◽  
Contextual Information ◽  
Network Technology ◽  
Context Aware ◽  
Individual Privacy ◽  
Network Technologies

Incorporate contextual information into recommendation systems can obtain better accuracy of recommendation, however, the users’ individual privacy may be disclosed by attackers. In order to resolve this problem, the authors propose a context-aware recommendation system that integrates Differential Privacy and Bayesian Network technologies (DPBCF). Firstly, the paper uses k-means algorithm to cluster items to relieve sparsity of rating matrix. Next, for the sake of protecting users’ privacy, the paper adds Laplace noises to ratings. And then adopts Bayesian Network technology to calculate the probability that users like a type of item with contextual information. At last, the authors illustrate the experimental evaluations to show that the proposed algorithm can provide a stronger privacy protection while improving the accuracy of recommendations.

Context-Aware Recommender Systems

2012 ◽  
Vol 23 (1) ◽  
pp. 1-20 ◽  
Author(s):  
Li-Cai WANG ◽  
Xiang-Wu MENG ◽  
Yu-Jie ZHANG
Keyword(s):  
Recommender Systems ◽  
Context Aware
Sign in / Sign up

Export Citation Format

Share Document