X-SPIDE: An eXplainable Machine Learning Pipeline for Detecting Smart Ponzi Contracts in Ethereum

Blockchain technology is revolutionizing digital asset exchange by eliminating the need for central authority control. However, the decentralized nature of blockchain attracts malicious actors, leading to the proliferation of financial scams, with Ponzi schemes being particularly prevalent. Conseque...

Full description

Saved in:
Bibliographic Details
Main Authors: Luca Pennella, Fabio Pinelli, Letterio Galletta
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/11003052/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849320955613020160
author Luca Pennella
Fabio Pinelli
Letterio Galletta
author_facet Luca Pennella
Fabio Pinelli
Letterio Galletta
author_sort Luca Pennella
collection DOAJ
description Blockchain technology is revolutionizing digital asset exchange by eliminating the need for central authority control. However, the decentralized nature of blockchain attracts malicious actors, leading to the proliferation of financial scams, with Ponzi schemes being particularly prevalent. Consequently, there is a growing need to develop automatic detection mechanisms for such scams. So far, the problem has been tackled by considering only classifier performances and with limited focus on the explanation and interpretation of the results. However, interpretability and explainability are crucial when classifier decisions may have economic consequences. This paper introduces X-SPIDE (XAI Smart Ponzi Identification and Detection), an explainable machine learning pipeline for Ponzi scheme detection within the Ethereum blockchain that aims to find the trade-off between performance and explainability. X-SPIDE allows for comparing the results of different classifiers, identifying a small set of features that offer strong performance, and understanding how these features contribute to classification — highlighting specific characteristics of malicious contracts. Moreover, we introduce and make publicly available a new comprehensive dataset comprising 7446 smart contracts, incorporating features derived from transaction history, creation, and deployment bytecodes to train and test our pipeline.
format Article
id doaj-art-750a5b2ec78d48fcbf4dc4a34211d385
institution Kabale University
issn 2169-3536
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-750a5b2ec78d48fcbf4dc4a34211d3852025-08-20T03:49:55ZengIEEEIEEE Access2169-35362025-01-0113850378505510.1109/ACCESS.2025.356956511003052X-SPIDE: An eXplainable Machine Learning Pipeline for Detecting Smart Ponzi Contracts in EthereumLuca Pennella0https://orcid.org/0009-0006-2721-1248Fabio Pinelli1https://orcid.org/0000-0003-1058-6917Letterio Galletta2https://orcid.org/0000-0003-0351-9169Department of Economics, Business, Mathematics and Statistics, University of Trieste, Trieste, ItalyIMT School for Advanced Studies Lucca, Lucca, ItalyIMT School for Advanced Studies Lucca, Lucca, ItalyBlockchain technology is revolutionizing digital asset exchange by eliminating the need for central authority control. However, the decentralized nature of blockchain attracts malicious actors, leading to the proliferation of financial scams, with Ponzi schemes being particularly prevalent. Consequently, there is a growing need to develop automatic detection mechanisms for such scams. So far, the problem has been tackled by considering only classifier performances and with limited focus on the explanation and interpretation of the results. However, interpretability and explainability are crucial when classifier decisions may have economic consequences. This paper introduces X-SPIDE (XAI Smart Ponzi Identification and Detection), an explainable machine learning pipeline for Ponzi scheme detection within the Ethereum blockchain that aims to find the trade-off between performance and explainability. X-SPIDE allows for comparing the results of different classifiers, identifying a small set of features that offer strong performance, and understanding how these features contribute to classification — highlighting specific characteristics of malicious contracts. Moreover, we introduce and make publicly available a new comprehensive dataset comprising 7446 smart contracts, incorporating features derived from transaction history, creation, and deployment bytecodes to train and test our pipeline.https://ieeexplore.ieee.org/document/11003052/Anomaly detectionblockchaincode featureseXplainable AIfraud detection
spellingShingle Luca Pennella
Fabio Pinelli
Letterio Galletta
X-SPIDE: An eXplainable Machine Learning Pipeline for Detecting Smart Ponzi Contracts in Ethereum
IEEE Access
Anomaly detection
blockchain
code features
eXplainable AI
fraud detection
title X-SPIDE: An eXplainable Machine Learning Pipeline for Detecting Smart Ponzi Contracts in Ethereum
title_full X-SPIDE: An eXplainable Machine Learning Pipeline for Detecting Smart Ponzi Contracts in Ethereum
title_fullStr X-SPIDE: An eXplainable Machine Learning Pipeline for Detecting Smart Ponzi Contracts in Ethereum
title_full_unstemmed X-SPIDE: An eXplainable Machine Learning Pipeline for Detecting Smart Ponzi Contracts in Ethereum
title_short X-SPIDE: An eXplainable Machine Learning Pipeline for Detecting Smart Ponzi Contracts in Ethereum
title_sort x spide an explainable machine learning pipeline for detecting smart ponzi contracts in ethereum
topic Anomaly detection
blockchain
code features
eXplainable AI
fraud detection
url https://ieeexplore.ieee.org/document/11003052/
work_keys_str_mv AT lucapennella xspideanexplainablemachinelearningpipelinefordetectingsmartponzicontractsinethereum
AT fabiopinelli xspideanexplainablemachinelearningpipelinefordetectingsmartponzicontractsinethereum
AT letteriogalletta xspideanexplainablemachinelearningpipelinefordetectingsmartponzicontractsinethereum