It’s All Connected: Detecting Phishing Transaction Records on Ethereum Using Link Prediction

Chidimma Opara; Yingke Chen; Bo Wei

doi:10.1007/978-3-031-27409-1_107

It’s All Connected: Detecting Phishing Transaction Records on Ethereum Using Link Prediction

Chidimma Opara, Yingke Chen, Bo Wei

Department of Computing & Games

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

29 Downloads (Pure)

Abstract

Digital currencies are increasingly being used on platforms for virtual transactions, such as Ethereum, owing to new financial innovations. As these platforms are anonymous and easy to use, they are perfect places for phishing scams to grow. Unlike traditional phishing detection approaches that aim to distinguish phishing websites and emails using their HTML content and URLs, phishing attacks on Ethereum focus on detecting phishing addresses by analyzing the transaction relationships on the virtual transaction platform. This study proposes a link prediction framework for detecting phishing transactions on the Ethereum platform using 12 local network-based features extracted from the Ether receiving and initiating addresses. The framework was trained and tested on over 280,000 verified phishing and legitimate transaction records. Experimental results indicate that the proposed framework with a LightGBM classifier provides a high recall of 89% and an AUC score of 93%.

Original language	English
Title of host publication	Hybrid Intelligent Systems
Subtitle of host publication	22nd International Conference on Hybrid Intelligent Systems (HIS 2022), December 13–15, 2022
Editors	Ajith Abraham, Tzung-Pei Hong, Ketan Kotecha, Kun Ma, Pooja Manghirmalani Mishra, Niketa Gandhi
Publisher	Springer
Pages	1167-1178
ISBN (Electronic)	9783031274091
ISBN (Print)	9783031274084
DOIs	https://doi.org/10.1007/978-3-031-27409-1_107
Publication status	Published - 25 May 2023
Event	22nd International Conference on Hybrid Intelligent Systems: On the World Wide Web - Online Duration: 13 Dec 2022 → 15 Dec 2022 https://www.mirlabs.org/his22/

Publication series

Name	Lecture Notes in Networks and Systems
Volume	647
ISSN (Print)	2367-3370
ISSN (Electronic)	2367-3389

Conference

Conference	22nd International Conference on Hybrid Intelligent Systems
Abbreviated title	HIS 2022
Period	13/12/22 → 15/12/22
Internet address	https://www.mirlabs.org/his22/

Access to Document

10.1007/978-3-031-27409-1_107Licence: Unspecified

Full textAccepted author manuscript, 927 KB

https://link.springer.com/chapter/10.1007/978-3-031-27409-1_107#copyright-informationLicence: Unspecified

Cite this

Opara, C., Chen, Y., & Wei, B. (2023). It’s All Connected: Detecting Phishing Transaction Records on Ethereum Using Link Prediction. In A. Abraham, T.-P. Hong, K. Kotecha, K. Ma, P. Manghirmalani Mishra, & N. Gandhi (Eds.), Hybrid Intelligent Systems: 22nd International Conference on Hybrid Intelligent Systems (HIS 2022), December 13–15, 2022 (pp. 1167-1178). (Lecture Notes in Networks and Systems; Vol. 647). Springer. https://doi.org/10.1007/978-3-031-27409-1_107

Opara, Chidimma ; Chen, Yingke ; Wei, Bo. / It’s All Connected: Detecting Phishing Transaction Records on Ethereum Using Link Prediction. Hybrid Intelligent Systems: 22nd International Conference on Hybrid Intelligent Systems (HIS 2022), December 13–15, 2022. editor / Ajith Abraham ; Tzung-Pei Hong ; Ketan Kotecha ; Kun Ma ; Pooja Manghirmalani Mishra ; Niketa Gandhi. Springer, 2023. pp. 1167-1178 (Lecture Notes in Networks and Systems).

@inproceedings{7efeb3c60d594e96b31501b9e7632e93,

title = "It{\textquoteright}s All Connected: Detecting Phishing Transaction Records on Ethereum Using Link Prediction",

abstract = "Digital currencies are increasingly being used on platforms for virtual transactions, such as Ethereum, owing to new financial innovations. As these platforms are anonymous and easy to use, they are perfect places for phishing scams to grow. Unlike traditional phishing detection approaches that aim to distinguish phishing websites and emails using their HTML content and URLs, phishing attacks on Ethereum focus on detecting phishing addresses by analyzing the transaction relationships on the virtual transaction platform. This study proposes a link prediction framework for detecting phishing transactions on the Ethereum platform using 12 local network-based features extracted from the Ether receiving and initiating addresses. The framework was trained and tested on over 280,000 verified phishing and legitimate transaction records. Experimental results indicate that the proposed framework with a LightGBM classifier provides a high recall of 89% and an AUC score of 93%.",

author = "Chidimma Opara and Yingke Chen and Bo Wei",

year = "2023",

month = may,

day = "25",

doi = "10.1007/978-3-031-27409-1_107",

language = "English",

isbn = "9783031274084",

series = "Lecture Notes in Networks and Systems",

publisher = "Springer",

pages = "1167--1178",

editor = "Abraham, {Ajith } and Hong, {Tzung-Pei } and Kotecha, {Ketan } and Ma, {Kun } and {Manghirmalani Mishra}, {Pooja } and Niketa Gandhi",

booktitle = "Hybrid Intelligent Systems",

note = "22nd International Conference on Hybrid Intelligent Systems : On the World Wide Web, HIS 2022 ; Conference date: 13-12-2022 Through 15-12-2022",

url = "https://www.mirlabs.org/his22/",

}

Opara, C, Chen, Y & Wei, B 2023, It’s All Connected: Detecting Phishing Transaction Records on Ethereum Using Link Prediction. in A Abraham, T-P Hong, K Kotecha, K Ma, P Manghirmalani Mishra & N Gandhi (eds), Hybrid Intelligent Systems: 22nd International Conference on Hybrid Intelligent Systems (HIS 2022), December 13–15, 2022. Lecture Notes in Networks and Systems, vol. 647, Springer, pp. 1167-1178, 22nd International Conference on Hybrid Intelligent Systems, 13/12/22. https://doi.org/10.1007/978-3-031-27409-1_107

It’s All Connected: Detecting Phishing Transaction Records on Ethereum Using Link Prediction. / Opara, Chidimma; Chen, Yingke; Wei, Bo.
Hybrid Intelligent Systems: 22nd International Conference on Hybrid Intelligent Systems (HIS 2022), December 13–15, 2022. ed. / Ajith Abraham; Tzung-Pei Hong; Ketan Kotecha; Kun Ma; Pooja Manghirmalani Mishra; Niketa Gandhi. Springer, 2023. p. 1167-1178 (Lecture Notes in Networks and Systems; Vol. 647).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - It’s All Connected: Detecting Phishing Transaction Records on Ethereum Using Link Prediction

AU - Opara, Chidimma

AU - Chen, Yingke

AU - Wei, Bo

PY - 2023/5/25

Y1 - 2023/5/25

N2 - Digital currencies are increasingly being used on platforms for virtual transactions, such as Ethereum, owing to new financial innovations. As these platforms are anonymous and easy to use, they are perfect places for phishing scams to grow. Unlike traditional phishing detection approaches that aim to distinguish phishing websites and emails using their HTML content and URLs, phishing attacks on Ethereum focus on detecting phishing addresses by analyzing the transaction relationships on the virtual transaction platform. This study proposes a link prediction framework for detecting phishing transactions on the Ethereum platform using 12 local network-based features extracted from the Ether receiving and initiating addresses. The framework was trained and tested on over 280,000 verified phishing and legitimate transaction records. Experimental results indicate that the proposed framework with a LightGBM classifier provides a high recall of 89% and an AUC score of 93%.

AB - Digital currencies are increasingly being used on platforms for virtual transactions, such as Ethereum, owing to new financial innovations. As these platforms are anonymous and easy to use, they are perfect places for phishing scams to grow. Unlike traditional phishing detection approaches that aim to distinguish phishing websites and emails using their HTML content and URLs, phishing attacks on Ethereum focus on detecting phishing addresses by analyzing the transaction relationships on the virtual transaction platform. This study proposes a link prediction framework for detecting phishing transactions on the Ethereum platform using 12 local network-based features extracted from the Ether receiving and initiating addresses. The framework was trained and tested on over 280,000 verified phishing and legitimate transaction records. Experimental results indicate that the proposed framework with a LightGBM classifier provides a high recall of 89% and an AUC score of 93%.

U2 - 10.1007/978-3-031-27409-1_107

DO - 10.1007/978-3-031-27409-1_107

M3 - Conference contribution

SN - 9783031274084

T3 - Lecture Notes in Networks and Systems

SP - 1167

EP - 1178

BT - Hybrid Intelligent Systems

A2 - Abraham, Ajith

A2 - Hong, Tzung-Pei

A2 - Kotecha, Ketan

A2 - Ma, Kun

A2 - Manghirmalani Mishra, Pooja

A2 - Gandhi, Niketa

PB - Springer

T2 - 22nd International Conference on Hybrid Intelligent Systems

Y2 - 13 December 2022 through 15 December 2022

ER -

Opara C, Chen Y, Wei B. It’s All Connected: Detecting Phishing Transaction Records on Ethereum Using Link Prediction. In Abraham A, Hong TP, Kotecha K, Ma K, Manghirmalani Mishra P, Gandhi N, editors, Hybrid Intelligent Systems: 22nd International Conference on Hybrid Intelligent Systems (HIS 2022), December 13–15, 2022. Springer. 2023. p. 1167-1178. (Lecture Notes in Networks and Systems). doi: 10.1007/978-3-031-27409-1_107

It’s All Connected: Detecting Phishing Transaction Records on Ethereum Using Link Prediction

Abstract

Publication series

Conference

Access to Document

Fingerprint

Cite this