Abstract:

Individual privacy can be breached if social networks are released directly. So privacy protection should be carried on. The privacy protection method named (k,2)-anonymity publication is proposed. The method is suitable for the scene that the aggressor with background knowledge of neighborhood information wants to identify sensitive edges in published social networks. The minimum structural modification is performed on origin social networks graphs and the largest amount of information from the published networks is obtained. Design and implement the algorithm meeting privacy preservation requirements of the published anonymously and carry on experiment on dataset to validate. Experimental results show that the method can effectively resist the sensitive edges identify attack and get acceptable release quality.

Key words: LAN Li-hui^1,2, SUN Ying-hui¹, JU Shi-guang²