Protection of User Data by Differential Privacy Algorithms

Abstract

With the emergence of more and more social software users, increasingly larger social networks have appeared. These social networks contain a large number of sensitive information of users, so privacy protection processing is needed before releasing social network information. This paper introduced the hierarchical random graph (HRG) based differential privacy algorithm and the single-source shortest path based differential privacy algorithm. Then, the performance of the two algorithms was tested by two artificial networks without weight, which was generated by LFR tool and two real networks with weight, which were crawled by crawler software. The results show that after processing the social network through the differential privacy algorithm, the average clustering coefficient decreases, and the expected distortion increases. The smaller the privacy budget, the higher the reduction and the more significant the increase. Under the same privacy budget, the average clustering coefficient and expected distortion of the single-source shortest path differential privacy algorithm are small. In terms of execution efficiency, the larger the size of the social network, the more time it takes, and the differential privacy algorithm based on the single-source shortest path spends less time in the same network.