Comprehensive Evaluation of Adversarial Perturbations against ML-Based Ethereum Phishing Detection Systems
Distributed Ledger Technologies: Research and Practice · 31.12.2026 · 5 (4) · 1-28
DOI: 10.1145/3772088 ↗Kurz gefasst
Fachartikel in der Zeitschrift Distributed Ledger Technologies: Research and Practice, online erschienen am 10.06.2026. Verfasst von Ahod Alghuried und 6 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 62 Literaturangaben.
Abstract (Originalsprache)
Machine Learning (ML) models are increasingly deployed to detect fraudulent activities in Ethereum, where phishing and scamming attacks pose serious security risks. Despite their promise, these models remain susceptible to adversarial manipulations. In this article, we present a comprehensive evaluation of ML-based Ethereum phishing detectors under a spectrum of adversarial perturbations. Our study examines multiple classifiers, including Random Forest, Decision Tree, K-Nearest Neighbors, Graph Neural Networks, and XGBoost, against rule-based, gradient-based, and black-box adversarial attacks. We conduct detailed feature-level analyses to identify transaction attributes most vulnerable to manipulation, and we evaluate the comparative robustness of classifiers under both targeted and untargeted attack scenarios. To strengthen model resilience, we assess mitigation techniques such as adversarial training and randomized smoothing, demonstrating their effectiveness in improving robustness without significant performance degradation.
Zitieren
APA
Alghuried, A., Alkinoon, A., Alghamdi, A., Choi, S., Camarato, S., Mohaisen, M., & Mohaisen, D. (2026). Comprehensive Evaluation of Adversarial Perturbations against ML-Based Ethereum Phishing Detection Systems. Distributed Ledger Technologies: Research and Practice, 5(4), 1-28. https://doi.org/10.1145/3772088
Vancouver
Alghuried A, Alkinoon A, Alghamdi A, Choi S, Camarato S, Mohaisen M, et al. Comprehensive Evaluation of Adversarial Perturbations against ML-Based Ethereum Phishing Detection Systems. Distributed Ledger Technologies: Research and Practice. 2026;5(4):1-28. doi:10.1145/3772088
BibTeX
@article{Alghuried2026,
author = {Alghuried, Ahod and Alkinoon, Ali and Alghamdi, Abdulaziz and Choi, Soohyeon and Camarato, Steffen and Mohaisen, Manar and Mohaisen, David},
title = {Comprehensive Evaluation of Adversarial Perturbations against ML-Based Ethereum Phishing Detection Systems},
journal = {Distributed Ledger Technologies: Research and Practice},
year = {2026},
volume = {5},
number = {4},
pages = {1--28},
doi = {10.1145/3772088}
}
EUVIMED