Neural-based inexact graph de-anonymization

作     者：Guangxi Lu Kaiyang Li Xiaotong Wang Ziyue Liu Zhipeng Cai Wei Li 

作者机构：Department of Computer ScienceGeorgia State UniversityAtlantaUSA St.George’s SchoolVancouerCanada 

出 版 物：《High-Confidence Computing》 (高置信计算（英文）)

年 卷 期：2024年第4卷第1期

页      面：52-59页

核心收录：

学科分类：12[管理学] 1201[管理学-管理科学与工程(可授管理学、工学学位)] 081104[工学-模式识别与智能系统] 08[工学] 0835[工学-软件工程] 0811[工学-控制科学与工程] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：supported by the National Science Foundation of U.S.(2011845 2315596 and 2244219) 

主　　题：Graph de-anonymization Graph convolutional network Neural tensor network 

摘      要：Graph de-anonymization is a technique used to reveal connections between entities in anonymized graphs,which is crucial in detecting malicious activities,network analysis,social network analysis,and *** its paramount importance,conventional methods often grapple with inefficiencies and challenges tied to obtaining accurate query graph *** paper introduces a neural-based inexact graph de-anonymization,which comprises an embedding phase,a comparison phase,and a matching *** embedding phase uses a graph convolutional network to generate embedding vectors for both the query and anonymized *** comparison phase uses a neural tensor network to ascertain node *** matching procedure employs a refined greedy algorithm to discern optimal node ***,we comprehensively evaluate its performance via well-conducted experiments on various real *** results demonstrate the effectiveness of our proposed approach in enhancing the efficiency and performance of graph de-anonymization through the use of graph embedding vectors.