A privacy preserving method based on random projection for social networks

Social networks consist of entities connected by links representing relations. The researchers can benefit through social networks analysis, however, it also brings about certain risks for the people involved in them. We put forward a privacy preserving method for weighted social networks based on random projection. The method described social networks as high dimensional edge spaces and adopted random projection matrixes to achieve mapping from higher dimension to lower dimension. Random projection matrixes were generated using hash function. The experimental results on the real datasets and synthetic datasets demonstrate that the edge space random projection method can ensure privacy information security and protect some structure characteristics of social networks analysis.