International Journal of Computer Applications (0975 – 8887) Volume 99– No.1, August 2014 40 Protecting Sensitive Labels in Social Network Data Navnath S. Bagal Post Graduate Student, Department of Computer Engg. PVPIT Bavdhan Pune-21 Navnath D. Kale Assistant Professor, Department of Computer Engg. PVPIT Bavdhan Pune-21 ABSTRACT Privacy is one of the major concerns when publishing or sharing social network data for social science research and business analysis. Recently, researchers have developed privacy models similar to k-anonymity to prevent node re- identification through structure information. However, even when these privacy models are enforced, an attacker may still be able to infer one’s private information if a group of nodes largely share the same sensitive labels (i.e., attributes). In other words, the label-node relationship is not well protected by pure structure anonymization methods. Furthermore, existing approaches, which rely on edge editing or node clustering, may significantly alter key graph properties. In this paper, we define a k-degree-l-diversity anonymity model that considers the protection of structural information as well as sensitive labels of individuals. We had seen a novel anonymization methodology based on adding noise nodes. We implemented that algorithm by adding noise nodes into the original graph with the consideration of introducing the least distortion to graph properties. We here propose novel approach to reduce number of noise node so that decrease the complexity within networks. We implement this protection model in a distributed environment, where different publishers publish their data independently Most importantly, we provide a rigorous analysis of the theoretical bounds on the number of noise nodes added and their impacts on an important graph property. We conduct extensive experiments to evaluate the effectiveness of the proposed technique. General Terms Protecting sensitive information using KDLD technique and graph increase/decrease, label setting, sequence generation algorithms. Keywords Privacy, Online Social Network, Privacy protecting in SN, Sensitive information 1. INTRODUCTION Protecting the privacy of personal information is one of the biggest challenges facing website developers, especially social network providers. Several researchers have discussed the issue of privacy. In today’s internet determined the people we have witnessed the rapid growth of online social networking sites (OSN) as well as their integration into our everyday life. OSN such as Facebook (FB), Twitter, LinkedIn, Myspace etc. now represent a fundamental shift in the way that we communicate in our personal and working live. With the sharing nature of OSN’s and the sites’ control of posted information and personal relationships, concerns have developed regarding trust and privacy issues within social networking. Mainly, the data may contain sensitive information about individuals that cannot be disclosed without compromising their confidentiality. This paper we use AES algorithm to encrypt sensitive attributes and attribute names. We used unique token (key) per user, therefore, prevents potential leaks of sensitive labels and information associated with them. Because it will be publish in encrypted format. We consider a graph model in every vertex of graph is linked with sensitive labels or private information. We develop a new algorithm (heuristic search) by adding noise nodes into the original graph without change original graph drastically, and provide security of each user & its sensitive data. Fig. a) Original graph SN b)2-degree anonymous graph c) 2degree 2-diversity graph SN Fig. 1a shows an example of a possible structure attack using degree collect the information. If an adversary knows that one person has three friends in a graph, he can know that node 2 is that person and the related attributes of node 2 are revealed. K-degree anonymity can be used to prevent such structured attacks in SN. However, in many applications in, a social network where each node has sensitive attributes should be published. For example, a graph may contain the user salaries which are sensitive. In this case, k-degree alone is not sufficient to prevent the inference of sensitive attributes of individuals. Fig. 1b shows a graph that satisfies 2-degree anonymity but node labels are not consider in a graph. In it, nodes 2 and 3 have the same degree 3, but they both have the label “80K.” If an attacker knows someone has three friends in the social networks, he can conclude that this person’s salary is 80K without exactly re-identify the node. Therefore, when sensitive labels are considered, the l-diversity should be adopted for graphs. Again, the l-diversity concept here has the same meaning as that defined over tabular data. 2. LITERATURE REVIEW Online social Networks have always been an important component of our daily life, but currently that more and more people are connected to the Internet, and their online counterpart is satisfying an increasingly vital role. Consider a graph model where each vertex in the graph is associated with as the sensitive label or (private information). According to survey privacy related issues in social networking is very important. Since this work explores the Preserving privacy in publishing social network data becomes an important concern. With some local knowledge about individuals in a social network, an adversary may attack the privacy of some victims