ANNM: A New Method for Adding Noise Nodes Which are Used Recently in Anonymization Methods in Social Networks

One of the main concerns at the time of production or share of information on social networking sites for scientific research and business analysis is privacy. Recently, different models of privacy such as k-anonymity have been created by researchers to avoid detection by using structural information. But still, attackers may be able to access private information by observing the behavior of some nodes in social networks. Current approaches that mainly focus on creating anonymity by edge editing or clustering may significantly change the properties of the social network graph. According to studies of Yuan et al. (IEEE Trans Knowl Data Eng 25(3):633–647, 2013), that makes anonymity with adding noise nodes, we decided to present a new method for adding noise nodes with least changes in main graph attributes. We used betweenness centrality measurement to prioritize the creation of noise nodes and considered the amount of their impact on graph properties. The result of comparing our proposed solution and other related works shows that the structural properties of the original social network graph have had very little change.

[1]  Alex Bavelas,et al.  Communication Patterns in Task‐Oriented Groups , 1950 .

[2]  Danfeng Yao,et al.  The union-split algorithm and cluster-based anonymization of social networks , 2009, ASIACCS '09.

[3]  Philip S. Yu,et al.  Protecting Sensitive Labels in Social Network Data Anonymization , 2013, IEEE Transactions on Knowledge and Data Engineering.

[4]  Amirreza Masoumzadeh,et al.  Preserving Structural Properties in Edge-Perturbing Anonymization Techniques for Social Networks , 2012, IEEE Transactions on Dependable and Secure Computing.

[5]  K. Liu,et al.  Towards identity anonymization on graphs , 2008, SIGMOD Conference.

[6]  Xiaowei Ying,et al.  Comparisons of randomization and K-degree anonymization schemes for privacy preserving social network publishing , 2009, SNA-KDD '09.

[7]  Latanya Sweeney,et al.  k-Anonymity: A Model for Protecting Privacy , 2002, Int. J. Uncertain. Fuzziness Knowl. Based Syst..

[8]  Gert Sabidussi,et al.  The centrality index of a graph , 1966 .

[9]  Donald F. Towsley,et al.  Resisting structural re-identification in anonymized social networks , 2008, The VLDB Journal.

[10]  Vijayalakshmi Atluri,et al.  Preserving Privacy in Social Networks: A Structure-Aware Approach , 2009, 2009 IEEE/WIC/ACM International Joint Conference on Web Intelligence and Intelligent Agent Technology.

[11]  Leonard M. Freeman,et al.  A set of measures of centrality based upon betweenness , 1977 .

[12]  Jemal H. Abawajy,et al.  Privacy Preserving Social Network Data Publication , 2016, IEEE Communications Surveys & Tutorials.

[13]  Sushant S. Khopkar,et al.  A penalty box approach for approximation betweenness and closeness centrality algorithms , 2015, Social Network Analysis and Mining.

[14]  B. K. Tripathy,et al.  Alpha-anonymization techniques for privacy preservation in social networks , 2016, Social Network Analysis and Mining.

[15]  Linlin Chen,et al.  Social Network De-Anonymization and Privacy Inference with Knowledge Graph Model , 2019, IEEE Transactions on Dependable and Secure Computing.

[16]  Alina Campan,et al.  A Clustering Approach for Data and Structural Anonymity in Social Networks , 2008 .

[17]  Jian Pei,et al.  Preserving Privacy in Social Networks Against Neighborhood Attacks , 2008, 2008 IEEE 24th International Conference on Data Engineering.

[18]  Jian Pei,et al.  The k-anonymity and l-diversity approaches for privacy preservation in social networks against neighborhood attacks , 2011, Knowledge and Information Systems.

[19]  Lei Zou,et al.  K-Automorphism: A General Framework For Privacy Preserving Network Publication , 2009, Proc. VLDB Endow..