A method and system for identifying abnormal transactions in swarm smart contracts based on multi-level

Abstract

The invention discloses a method and system for identifying abnormal transactions based on multi-level swarm smart contracts. In the stages of multi-level transaction flow capture and feature extraction, a method for dual feature sets of sequence features and attribute features between a client and related nodes is proposed. , quantify the transaction characteristics, and improve the accuracy of the transaction description of each node. Secondly, in the feature selection stage, "more deletion and less supplementation" and information gain rate are proposed, redundant features are deleted, and the feature space of transaction flow data is reduced, thereby reducing time consumption and improving efficiency; finally, in the training and detection model stage, an adaptive k value is adopted The abnormal point detection algorithm analyzes the data after the feature selection, and obtains the analysis results of the transaction flow data, so as to realize the detection of abnormal transactions in the group smart contract. Moreover, the abnormal transaction detection method processes and analyzes the extracted sequence features and attribute features, which greatly improves the performance and applicability of the current detection system.

Description

technical field [0001] The invention belongs to network security technology, and in particular relates to a multi-level group smart contract abnormal transaction identification method and identification system. Background technique [0002] With the popularization of blockchain technology and the continuous expansion of the demand for smart service transaction supervision, the transaction security of group smart contracts has attracted more and more attention. In order to ensure the security of swarm smart contract transactions, the corresponding business systems usually have a detection mechanism for transaction behavior, such as intercepting possible risky transactions in the business system by detecting malicious nodes of swarm smart contract. With the continuous improvement of network technology, there are more and more attack methods such as viruses or Trojan horse programs, and it is difficult to cover all possible network attacks or other risky transactions in a timel...

AI Technical Summary

Problems solved by technology

With the continuous improvement of network technology, there are more and more attack methods such as viruses or Trojan horse programs, but it is difficult to detect malicious nodes in a timely manner to cover all possible network attacks or other risky transactions. In practical applications, users May be used by malicious security nodes to complete risky transactions, causing losses to users

Images