Splitting Anonymity:the Research And Implementation Of A Novel Privacy Preserving Approach For Social Network

Large amount of personal social information are collected and published due to the rapid development of social network techniques and applications, and thus it is quite essential to take privacy preservation and prevent sensitive information leakage. Focusing too much on the preservation level to privacy, most of current anonymous techniques cannot provide accurate answers to utility queries even at high price.With detailed study of popular anonymities and analysis of their shortcomings, a novel anonymous approach called Splitting Anonymity is introduced in this paper to point against the contradiction of privacy and utility. Splitting anonymity designed in this paper provides a high level preservation only to the privacy of social network data that is unknown to attackers, which avoids the low utility caused by the noises forced on knowledge that is already known to attackers. With the information hiding technique introduced from cryptography, splitting anonymity discards some inferior processing methods like destroying the social network’s structure and removing privacy directly only to achieve the level of security. And that makes splitting anonymity possess outstanding features, such as universal scalability and dynamic anonymous support. Splitting anonymity is of efficiency for anonymous process, and the data generated by splitting anonymity is of high security for privacy and accuracy for utility queries. Both detailed algorithms and query strategies of utility are provided in this paper, and strict theoretical analysis for privacy and utility are included. Dynamic anonymity support is an essential feature of splitting anonymity to go beyond existing anonymities. Dynamic anonymity support leads to not only the parallel processing, but low anonymity cost for dynamic data as well.Large amount of evaluation results based on real datasets verified the design of this paper that data processed by splitting anonymity can refuse any direct attack, and the strategies are also safe enough to indirect attacks with high utility.