Turkish Journal of Electrical Engineering and Computer Sciences




Deep learning models are widely being used to provide relevant recommendations in hybrid recommender systems. These hybrid systems combine the advantages of both content based and collaborative filtering approaches. However, these learning systems hamper the user privacy and disclose sensitive information. This paper proposes a privacy preserving deep learning based hybrid recommender system. In hybrid deep neural network, user?s side information such as age, location, occupation, zip code along with user rating is embedded and provided as input. These embedding?s pose a severe threat to individual privacy. In order to eliminate this breach of privacy, we have proposed a private embedding scheme that protects user privacy while ensuring that the nonlinear latent factors are also learnt. In this paper, we address the privacy in hybrid system using differential privacy, a rigorous mathematical privacy mechanism in statistical and machine learning systems. In the reduced feature set, the proposed adaptive perturbation mechanism is used to achieve higher accuracy. The performance is evaluated using three datasets with root mean square error (RMSE), mean absolute error (MAE), mean squared error (MSE), R squared, precision and recall. These evaluation metrics are compared with varying values of privacy parameter ? . The experimental results show that the proposed solution provides high user privacy with reasonable accuracy than the existing system. As the engine is generic, it can be used on any recommendation framework.


Differential privacy, adaptive perturbation, private hybrid recommender, embedding perturbation, deep neural network, laplace noise, randomized response

First Page


Last Page