Digital currency transaction tracing method and device based on unsupervised learning technology

Abstract

The invention discloses a digital currency transaction traceability method and device based on an unsupervised learning technology. The method comprises the following steps: intercepting digital currency transaction flow sent or received between a target node and a peer node thereof; for each digital currency transaction involved in the intercepted flow, counting the number of transaction broadcast messages sent by the target node and the number of transaction request messages received by the target node, and constructing a feature vector of the digital currency transaction according to the counted number of messages; performing anomaly detection on the feature vector of each digital currency transaction by using an unsupervised anomaly detection algorithm; and tracing whether each digital currency transaction is created for the target node or not according to an anomaly detection result. According to the invention, the digital currency transaction traceability precision can be improved.

Description

technical field [0001] The present invention relates to the field of computer technology, in particular to a digital currency transaction traceability method and device based on unsupervised learning technology. Background technique [0002] As the initial realization of blockchain thought, digital currency led by digital currency has developed rapidly, and the scale of transactions has continued to rise. At the same time, digital currency has the characteristics of decentralization and anonymity, as well as the convenience that it allows users to send funds instantly anywhere in the world Therefore, it is necessary to study illegal digital currency, especially the transaction traceability technology of digital currency. [0003] The existing digital currency transaction traceability technology is mainly divided into two research directions: transaction layer traceability technology and network layer traceability technology. The transaction layer traceability technology ref...

AI Technical Summary

Problems solved by technology

[0006] In the existing digital currency traceability technology, the transaction layer traceability technology only realizes the clustering of transaction addresses that may belong to the same entity, and cannot obtain the identity information of anonymous digital currency users, and the degree of de-anonymization is not enough; while the traceability technology based on unsupervised learning It mainly uses network traffic analysis and anomaly detection algorithms to identify transactions created by nodes, and there is also the problem of low traceability accuracy. In addition, there may be a variety of abnormal behaviors in the detection data. Anomalies other than the target behavior are regarded as noise data, based on simple Supervised learning detection algorithms cannot distinguish it from the target behavior

Images