块链
数据库事务
鉴定(生物学)
计算机科学
特征(语言学)
拓扑(电路)
网络拓扑
数据挖掘
事务处理
分布式计算
计算机网络
计算机安全
工程类
数据库
语言学
哲学
植物
电气工程
生物
作者
Yuyu Yue,Jixin Zhang,Mingwu Zhang,Jia Yang
出处
期刊:Electronics
[MDPI AG]
日期:2024-04-09
卷期号:13 (8): 1416-1416
被引量:1
标识
DOI:10.3390/electronics13081416
摘要
Cryptocurrency, as one of the most successful applications of blockchain technology, has played a vital role in promoting the development of the digital economy. However, its anonymity, large scale of cryptographic transactions, and decentralization have also brought new challenges in identifying abnormal accounts and preventing abnormal transaction behaviors, such as money laundering, extortion, and market manipulation. Recently, some researchers have proposed efficient and accurate abnormal transaction detection based on machine learning. However, in reality, abnormal accounts and transactions are far less common than normal accounts and transactions, so it is difficult for the previous methods to detect abnormal accounts by training with such an imbalance in abnormal/normal accounts. To address the issues, in this paper, we propose a method for identifying abnormal accounts using topology analysis of cryptographic transactions. We consider the accounts and transactions in the blockchain as graph nodes and edges. Since the abnormal accounts may have special topology features, we extract topology features from the transaction graph. By analyzing the topology features of transactions, we discover that the high-dimensional sparse topology features can be compressed by using the singular value decomposition method for feature dimension reduction. Subsequently, we use the generative adversarial network to generate samples like abnormal accounts, which will be sent to the training dataset to produce an equilibrium of abnormal/normal accounts. Finally, we utilize several machine learning techniques to detect abnormal accounts in the blockchain. Our experimental results demonstrate that our method significantly improves the accuracy and recall rate for detecting abnormal accounts in blockchain compared with the state-of-the-art methods.
科研通智能强力驱动
Strongly Powered by AbleSci AI