Abstract
Releasing evolving networks which contain sensitive information could compromise individual privacy. In this paper, we study the problem of releasing evolving networks under differential privacy. We explore the possibility of designing a differentially private evolving networks releasing algorithm. We found that the majority of traditional methods provide a snapshot of the networks under differential privacy over a brief period of time. As the network structure only changes in local part, the amount of required noise entirely is large and it leads to an inefficient utility. To this end, we propose GHRG-DP, a novel differentially private evolving networks releasing algorithm which reduces the noise scale and achieves high data utility. In the GHRG-DP algorithm, we learn the online connection probabilities between vertices in the evolving networks by generalized hierarchical random graph (GHRG) model. To fit the dynamic environment, a dendrogram structure adjusting method in local areas is proposed to reduce the noise scale in the whole period of time. Moreover, to avoid the unhelpful outcome of the connection probabilities, a Bayesian noisy probabilities calculating method is proposed. Through formal privacy analysis, we show that the GHRG-DP algorithm is ε -differentially private. Experiments on real evolving network datasets illustrate that GHRG-DP algorithm can privately release evolving networks with high accuracy.
Highlights
As more and more individual information in social network is published, releasing network data might pose threats to individual’s privacy
To make the generalized hierarchical random graph (GHRG)-DP satisfy differential privacy, we first sample a GHRG by a Markov chain Monte Carlo (MCMC) method by exponential mechanism while satisfying differential privacy. en, we adjust the GHRG by exponential mechanism while satisfying differential privacy as well. irdly, we add Laplace noise to the parameters for the model of the network. rough formal privacy analysis, we prove that GHRG-DP satisfies ε-differential privacy
Our solution is composed of two schemes: (1) we propose a dendrogram construction method for evolving network, called dendrogram construction based on adjustment (DCBA)
Summary
As more and more individual information in social network is published, releasing network data might pose threats to individual’s privacy. Ese synthetic network generation methods could “dilute” the impact of small changes of the network structure by capturing the connection probabilities between vertices. Given a sequence of evolving networks, the standard technique of differential privacy is to add noise to each snapshot of the evolving networks. Mathematical Problems in Engineering between vertices of the network may obtain unhelpful outcomes when the connection probabilities equal 0 or 1 To this end, we propose a novel differentially private evolving networks releasing algorithm, called GHRG-DP (i.e., differentially private based on generalized hierarchical random graph). To ensure that the releasing evolving networks under differential privacy do not incur excessive noise, we propose a method by adding noise to the parameters for the model of the network.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have