Return
Ensemble multi-label machine learning solidity smart contract vulnerability detection model
DOI:10.1007/s10586-025-05725-y.png)
Abstract
En 中文
Blockchain technology has revolutionized digital financial transactions and asset ownership by enabling decentralized and automated operations through smart contracts. Solidity smart contracts, used in the Ethereum blockchain network, facilitate secure and trustless execution of agreements. However, like any code, smart contracts are prone to vulnerabilities. Considering the assets and value of currency these smart contracts handle, their exploitation leads to severe financial losses and loss of operations. Such exploits have resulted in billions of dollars in stolen or locked assets. In this paper, we present an ensemble multilabel classifier model approach for the automated detection of vulnerabilities in Solidity smart contracts using a real smart contract dataset, with a detailed methodological process that includes processing the dataset. The proposed model stack achieves excellent results with F1 scores ranging from 82.0% to 99.9% for each vulnerability dataset. The proposed model is also compared with common static analyzer tools and models proposed in the literature following a similar approach. Moreover, we package the models into a web application, demonstrating deployment and functionality.
Keywords:
Smart contract
Blockchain
Solidity
Vulnerability detection
Etherlock
Reentrancy
Integer underflow/Overflow
Block dependency
Journal
C
IF:
0
Papers:
691
Citations:
1
Organization
Cited Papers
Strengthening the Security of Smart Contracts through the Power of Artificial Intelligence
Computers
IF0
An Integrated Smart Contract Vulnerability Detection Tool Using Multi-Layer Perceptron on Real-Time Solidity Smart Contracts
IEEE ACCESS
IF3.6

