Smart Contracts Vulnerability Classification through Deep Learning

Martina Rossini,Stefano Ferretti,Mirko Zichichi

doi:10.1145/3560905.3568175

Smart Contracts Vulnerability Classification through Deep Learning

Martina Rossini, Stefano Ferretti + Show 1 more

Open Access

https://doi.org/10.1145/3560905.3568175

Copy DOI

Publication Date: Nov 6, 2022

Citations: 1

Affiliation: University of Bologna, University of Urbino, Universidad Politécnica de Madrid

#Variants Of Convolutional Neural Networks #Convolutional Neural Networks + Show 8 more

Abstract
Full-Text PDF
Similar Papers

Abstract

We investigate the use of deep learning to classify smart contract code vulnerabilities. We use different variants of Convolutional Neural Networks (CNNs) and a Long Short-Term Memory (LSTM) neural network. Five classes of vulnerabilities were employed. Our results suggest that the CNNs are able to provide a good level of accuracy, thus showing the viability of the proposed approach.

Full Text