Abnormal Transactions Detection in the Ethereum Network Using Semi-Supervised Generative Adversarial Networks

Abstract

Numerous abnormal transactions have been exposed as a result of targeted attacks on Ethereum, such as the Ethereum Decentralized Autonomous Organization attack. Exploiting vulnerabilities in smart contracts, malicious users can pursue their own illicit objectives through abnormal transactions. Consequently, identifying these malevolent users, implicated in fraudulent activities and their attribution, becomes exceedingly complex. Cryptocurrency transactions used for malicious purposes, employing pseudo-anonymous accounts to send and receive ransom payments and accumulating funds under various identities, further highlight the need to control and detect these abnormal transactions for maintaining a high level of security within the Ethereum network. Although existing Intrusion Detection Systems (IDSs) help mitigate abnormal transaction occurrences, their performance necessitates improvement. To address this issue, this study presents a novel approach, named Abnormal Transactions Detection Using a Semi-Supervised Generative Adversarial Network (ATD-SGAN), which efficiently detects abnormal attacks within the Ethereum network. ATD-SGAN leverages a semi-supervised generative adversarial network for this purpose. The results demonstrate that ATD-SGAN significantly enhances the performance of state-ofthe-art IDSs. It achieves an increase in detection accuracy from 3.78% to 11.05% and reduces the false alarm rate from 42.29% to 0.15%. Moreover, ATD-SGAN notably improves the F1-measure, ranging from 10.39% to 3.79%, compared to the current IDSs.

An Abnormal Account Identification Method by Topology Feature Analysis for Blockchain-Based Transaction Network

“…Meanwhile, the existing literature is also relatively scarce in terms of comparative studies of different feature dimension reduction and data augmentation methods and their technical effectiveness in anomaly detection based on high-dimensional and sparse graph features in the blockchain. ✓ ✓ ✓ Liang et al [15] ✓ ✓ Ashfaq et al [16] ✓ ✓ ✓ Sanjalawe et al [17] ✓ ✓ ✓ Muhammad et al [18] ✓ ✓ Alarab et al [19] ✓ ✓ ✓ Sharma et al [20] ✓ ✓ ✓ Chen et al [21] ✓ ✓ ✓ Pourhabibi et al [22] ✓ Xiao et al [23] ✓ ✓ ✓ Liu et al [24] ✓ ✓ ✓ Alarab et al [25] ✓ ✓ Elbaghdadi et al [26] ✓ ✓ Nerurkar et al [27] ✓ ✓ Mohammed et al [28] ✓ ✓ Voronov et al [29] ✓ ✓ Venkatesan et al [30] ✓ ✓…”

“…To detect abnormal transactions in the blockchain, some machine learning methods have been employed, like active machine learning solutions (Lorenz et al [13]), a collaborative clustering-characteristic-based data fusion approach (Liang et al [15]), a secure fraud detection model based on XGboost and the random forest method (Ashfaq et al [16]), and using a semi-supervised generative adversarial network, which efficiently detects abnormal attacks within the Ethereum network (Sanjalawe et al [17]). In another method, the system integrates blockchain at base stations and cluster heads in a wireless sensor network to enhance security using a machine learning classifier called Histogram Gradient Boost to identify and revoke malicious nodes (Nouman et al [18]).…”

A Token-based Approach to Detect Fraud in Ethereum Transactions

“…Finally, the model, built on 80% of the training data, produced an accuracy of more than 96% on test data. The study by Yousef K., et al [13] presents a novel approach which efficiently detects abnormal attacks within the Ethereum network, named as ATD-SGAN. For this, a semi-supervised generative adversarial network was employed.…”