Securing blockchain-based crowdfunding platforms: an integrated graph neural networks and machine learning approach

Karim Zkik (), Anass Sebbar (), Oumaima Fadi (), Sachin Kamble () and Amine Belhadi ()
Additional contact information
Karim Zkik: ESAIP Ecole d’Ingenieur, CERADE
Anass Sebbar: International University of Rabat, TICLab, College of Engineering and Architecture
Oumaima Fadi: International University of Rabat, TICLab, College of Engineering and Architecture
Sachin Kamble: EDHEC Business School
Amine Belhadi: International University of Rabat, BEARLab, Rabat Business School

Electronic Commerce Research, 2024, vol. 24, issue 1, No 18, 497-533

Abstract: Abstract Blockchain-based crowdfunding is a form of crowdfunding that uses blockchain technology to facilitate the fundraising process. Blockchain technology provides a decentralized, transparent, and secure platform for crowdfunding by allowing the creation of smart contracts and the issuance of digital tokens. However, Blockchain-based crowdfunding systems suffer from a few security issues, such as the possibility of fraud, risk assessment, smart contracts bugs, and cyber-attacks. This paper proposes integrating artificial intelligence models to prevent smart contract vulnerabilities and anomaly detection. Thus, we will deploy Graph Neural Networks models to protect Blockchain-based crowdfunding platforms from smart contracts-based attacks such as reentrancy and infinite loop attacks. Then, we will use a machine learning model for anomaly detection and prevent attacks such as advanced persistent threats, malware, and distributed denial of service attacks. An experimental study is conducted in a real crowdfunding platform to prove the feasibility of our framework and to draw lessons from the real-life implementation of such models. Our results show that our approach can accurately identify both normal and abnormal traffic and classify correctly specific types of attacks. We also evaluate the performance of our framework using various evaluation metrics to ensure its effectiveness in detecting anomalies.

Keywords: Blockchain; Crowdfunding; Cybersecurity; Smart contract; Anomaly detection; Graph neural networks; Machine learning (search for similar items in EconPapers)
Date: 2024
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
http://link.springer.com/10.1007/s10660-023-09702-8 Abstract (text/html)
Access to the full text of the articles in this series is restricted.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:elcore:v:24:y:2024:i:1:d:10.1007_s10660-023-09702-8

Ordering information: This journal article can be ordered from
http://www.springer.com/journal/10660

DOI: 10.1007/s10660-023-09702-8

Access Statistics for this article

Electronic Commerce Research is currently edited by James Westland

More articles in Electronic Commerce Research from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().