Smart contract reentrant vulnerability detection method based on adversarial neural network

Abstract

The invention discloses a smart contract reentrant vulnerability detection method based on an adversarial neural network, and belongs to the technical field of block chain security. According to the method, extracting each type of vulnerability threat feature, and when the similarity between a contract statement and a vulnerability statement is greater than a threshold value, matching the contract statement and the vulnerability threat feature. And if matching succeeds, marking the contract statement with a vulnerability statement and recording the type of the vulnerability statement. If the matching fails, indicating that the misjudgment exists, and not marking the contract statement as a vulnerability statement. Through confrontation of the generator and the discriminator, the discriminator has good discrimination capability. According to the method, misjudgment of the vulnerability statements can be avoided, all the vulnerability statements in the intelligent contract library can be automatically searched, and the method has good accuracy.

Description

technical field [0001] The invention relates to a method for detecting a reentrant vulnerability of an intelligent contract based on an adversarial neural network, and belongs to the technical field of block chain security. Background technique [0002] Blockchain technology has many applications in modern information technology and computing environments. This technology has key characteristics such as decentralization, distribution, and tamper resistance, and has the ability to utilize distributed computing resources. A smart contract is a predefined piece of logic that automatically executes, controls, and records related events in the blockchain. The key functionality of smart contracts can ensure transactions are verified, payouts are settled, and malicious activity is detected and mitigated. [0003] Although smart contracts are widely used, there is no uniform standard for the order in which functions are executed in a blockchain system. Due to the lack of execution...

AI Technical Summary

Problems solved by technology

[0010] The purpose of the present invention is to overcome the technical defects such as low accuracy of existing reentrant vulnerability detection methods, and to solve the technical problem of effectively detecting reentrant vulnerabilities before deploying smart contracts, and creatively propose a method based on adversarial neural Smart contract reentrancy vulnerability detection method for the network

Images