Eth-PSD: A Machine Learning-Based Phishing Scam Detection Approach in Ethereum

Abstract

Recently, the rapid flourish of blockchain technology in the financial field has attracted many cybercriminals' attention to launch blockchain-based attacks such as Ponzi schemes, Scam wallets, and phishing scams. Currently, Ethereum is the most prominent blockchain-based platform and the first that supports smart contracts. However, the number of phishing scam accounts are reportedly more than 50% of all cybercrimes in Ethereum. In contrast, this paper proposes a detection mechanism called Ethereum Phishing Scam Detection (Eth-PSD) that attempts to detect phishing scam-related transactions using a novel machine learning-based approach. Eth-PSD tackles some of the limitations in the existing works, such as the use of imbalanced datasets, complex feature engineering, and lower detection accuracy. We also investigated the aspects of constructing a new updated and balanced dataset that can be used for evaluating Eth-PSD effectively. Our experimental results indicate that Eth-PSD could efficiently detect the phishing scam on Ethereum with a detection accuracy of 98.11%, with a very low False Positive Rate of 0.01. Taken together, Eth-PSD showed a superior advantage compared to the existing works in reducing the dimensionality of the dataset by feature engineering and achieved an overall detection accuracy with an improvement of at least 6% compared to other existing solutions from the related work.

Advanced Fraud Detection in Blockchain Transactions: An Ensemble Learning and Explainable AI Approach

“…The comparative evaluation of our proposed Ensemble Hard Voting classifier against other methods presented in the existing literature further underscores its superior performance (Table II). With an ACC of 99%, the proposed model surpasses the accuracies reported in [3,36,38,39,42]. Not only does this comparison illustrate the efficiency of the proposed model, but also demonstrates its contribution to the ongoing research in EFD.…”

“…The study successfully achieved high recall and precision values, which enabled the design of an effective antifraud rule for digital wallets or currency exchanges. This study introduces a novel detection mechanism called Ethereum Phishing Scam Detection (Eth-PSD) aimed at identifying phishing scam related transactions using an ML based approach [38]. Eth-PSD addresses various limitations present in existing works, including imbalanced datasets, complex feature engineering, and lower detection accuracy.…”

“…These findings emphasize the growing potential of ML-driven solutions in managing the intricate cybersecurity challenges within the constantly evolving BC sphere. 96.3% [36] 98% [42] 80.2% [38] 98.11% [39] 97.96%…”

Learning to Traverse Cryptocurrency Transaction Graphs Based on Transformer Network for Phishing Scam Detection

“…A study focused on collecting and pre-processing Ethereum address-by-address data and then implementing the K-nearest-neighbor algorithm demonstrated the effectiveness of traditional machine learning techniques in identifying scam nodes in cryptocurrency transactions [5]. A unique approach to applying time series models to Ethereum transaction data provided insights into the temporal aspects of Ethereum transactions and demonstrated the potential of time series analysis in this area [6].…”

Monitoring Peer-to-Peer Botnets: Requirements, Challenges, and Future Works

“…At the same time, the monitoring approaches are more accurate in terms of tracking the bots. An example of a common detection approach is the Intrusion Detection System (IDS) [26]. IDS is software that can identify attacks by distinguishing their intrusions as abnormal traffic [7,27].…”