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 more.Despite its p...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 more.Despite its paramount importance,conventional methods often grapple with inefficiencies and challenges tied to obtaining accurate query graph data.This paper introduces a neural-based inexact graph de-anonymization,which comprises an embedding phase,a comparison phase,and a matching procedure.The embedding phase uses a graph convolutional network to generate embedding vectors for both the query and anonymized graphs.The comparison phase uses a neural tensor network to ascertain node resemblances.The matching procedure employs a refined greedy algorithm to discern optimal node pairings.Additionally,we comprehensively evaluate its performance via well-conducted experiments on various real datasets.The 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.展开更多
The anonymity and de-anonymity of blockchain and Bitcoin have always been a hot topic in blockchain related research.Since Bitcoin was created by Nakamoto in 2009,it has,to some extent,deviated from its currency attri...The anonymity and de-anonymity of blockchain and Bitcoin have always been a hot topic in blockchain related research.Since Bitcoin was created by Nakamoto in 2009,it has,to some extent,deviated from its currency attribute as a trading medium but instead turned into an object for financial investment and operations.In this paper,the power-law distribution that the Bitcoin network obeys is given with mathematical proof,while traditional deanonymous methods such as clustering fail to satisfy it.Therefore,considering the profit-oriented characteristics of Bitcoin traders in such occasion,we put forward a de-anonymous heuristic approach that recognizes and analyzes the behavioral patterns of financial High-Frequency Transactions(HFT),with realtime exchange rate of Bitcoin involved.With heuristic approach used for de-anonymity,algorithm that deals with the adjacency matrix and transition probability matrix are also put forward,which then makes it possible to apply clustering to the IP matching method.Basing on the heuristic approach and additional algorithm for clustering,finally we established the de-anonymous method that matches the activity information of the IP with the transaction records in blockchain.Experiments on IP matching method are applied to the actual data.It turns out that similar behavioral pattern between IP and transaction records are shown,which indicates the superiority of IP matching method.展开更多
基金supported by the National Science Foundation of U.S.(2011845,2315596 and 2244219).
文摘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 more.Despite its paramount importance,conventional methods often grapple with inefficiencies and challenges tied to obtaining accurate query graph data.This paper introduces a neural-based inexact graph de-anonymization,which comprises an embedding phase,a comparison phase,and a matching procedure.The embedding phase uses a graph convolutional network to generate embedding vectors for both the query and anonymized graphs.The comparison phase uses a neural tensor network to ascertain node resemblances.The matching procedure employs a refined greedy algorithm to discern optimal node pairings.Additionally,we comprehensively evaluate its performance via well-conducted experiments on various real datasets.The 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.
基金supported by National Natural Science Foundation of China(No.62002332)。
文摘The anonymity and de-anonymity of blockchain and Bitcoin have always been a hot topic in blockchain related research.Since Bitcoin was created by Nakamoto in 2009,it has,to some extent,deviated from its currency attribute as a trading medium but instead turned into an object for financial investment and operations.In this paper,the power-law distribution that the Bitcoin network obeys is given with mathematical proof,while traditional deanonymous methods such as clustering fail to satisfy it.Therefore,considering the profit-oriented characteristics of Bitcoin traders in such occasion,we put forward a de-anonymous heuristic approach that recognizes and analyzes the behavioral patterns of financial High-Frequency Transactions(HFT),with realtime exchange rate of Bitcoin involved.With heuristic approach used for de-anonymity,algorithm that deals with the adjacency matrix and transition probability matrix are also put forward,which then makes it possible to apply clustering to the IP matching method.Basing on the heuristic approach and additional algorithm for clustering,finally we established the de-anonymous method that matches the activity information of the IP with the transaction records in blockchain.Experiments on IP matching method are applied to the actual data.It turns out that similar behavioral pattern between IP and transaction records are shown,which indicates the superiority of IP matching method.
