Seed-free Graph De-anonymiztiation with Adversarial Learning

Abstract

The huge amount of graph data are published and shared for research and business purposes, which brings great benefit for our society. However, user privacy is badly undermined even though user identity can be anonymized. Graph de-anonymization to identify nodes from an anonymized graph is widely adopted to evaluate users' privacy risks. Most existing de-anonymization methods which are heavily reliant on side information (e.g., seeds, user profiles, community labels) are unrealistic due to the difficulty of collecting this side information. A few graph de-anonymization methods only using structural information, called seed-free methods, have been proposed recently, which mainly take advantage of the local and manual features of nodes while overlooking the global structural information of the graph for de-anonymization. In this paper, a seed-free graph de-anonymization method is proposed, where a deep neural network is adopted to learn features and an adversarial framework is employed for node matching. To be specific, the latent representation of each node is obtained by graph autoencoder. Furthermore, an adversarial learning model is proposed to transform the embedding of the anonymized graph to the latent space of auxiliary graph embedding such that a linear mapping can be derived from a global perspective. Finally, the most similar node pairs in the latent space as the anchor nodes are utilized to launch propagation to de-anonymize all the remaining nodes. The extensive experiments on some real datasets demonstrate that our method is comparative with the seed-based approaches and outperforms the start-of-the-art seed-free method significantly.