Link deletion method for network structure privacy protection against link prediction

Abstract

The invention discloses a link deletion method for network structure privacy protection against link prediction. The link deletion method comprises the following steps: S1, selecting a plurality of target links from an original network link set; deleting all the target links from the original network link set; giving a deletion budget K and a link deletion counter i, wherein i = 0; S2, setting theinitial weight values of all links in the current network link set as 0; wherein the link deletion counter i = i + 1; S3, finding out a common neighbor of two end nodes of each target link; for eachtarget link, adding 1 to the weight value of the link between each end node and the common neighbor; S4, when the maximum weight value is greater than 0 and i is not greater than K, performing S5, ifnot, performing S7; S5, selecting a link with the maximum weight value and deleting the link; S6, updating the current network link set in the step S2, and returning to the step S2; S7, ending. According to the method, better availability reservation of an original network can be realized, and a very good privacy protection purpose can be achieved.

Description

technical field [0001] The invention belongs to the technical field of cyberspace security and privacy protection, and relates to a link deletion method for network structure privacy protection against link prediction. Background technique [0002] In today's digital age, data privacy leakage has become one of the most difficult network security issues. In particular, the privacy protection of social network structural data is particularly important, which is mainly reflected in two points: 1) social network structural data is the basis for people to study social networks; 2) some important links (or edges) in social networks are often It is sensitive, such as the private friendship between two users, and the leakage of privacy may cause huge mental distress or economic losses to the users. We call sensitive links in the network "target links" because they are often the target of attackers. Typically, target links are only a small fraction of all links. Of course, the use...

AI Technical Summary

Problems solved by technology

[0004] To sum up, the existing network structure perturbation methods have certain defects: 1. The availability of the network structure is greatly reduced

Because of the addition of false links, new network security issues have arisen in the network, such as false link detection; 2. The existing methods mainly consider the privacy protection of the overall network structure, that is, assuming that all links in the network need privacy protection, resulting in Privacy protection is not targeted, and the protection of important target links is insufficient

Images