Who Are the Phishers? Phishing Scam Detection on Ethereum via Network Embedding

TLDR

Blockchain technology has become a hotspot for cybercrime, with phishing scams on the platform generating significant profits and posing a serious threat to trading security. The study aims to develop an effective phishing‑scam detection method for Ethereum to foster a safer investment environment. By crawling phishing addresses from two authorized sites, reconstructing the transaction network, embedding transaction amounts and timestamps with the novel trans2vec algorithm, and applying a one‑class SVM, the authors classify addresses as normal or phishing. Experiments show the trans2vec‑based approach outperforms existing algorithms on Ethereum, demonstrating effective phishing detection and marking the first network‑embedding study of this kind.

Abstract

Recently, blockchain technology has become a topic in the spotlight but also a hotbed of various cybercrimes. Among them, phishing scams on blockchain have been found to make a notable amount of money, thus emerging as a serious threat to the trading security of the blockchain ecosystem. In order to create a favorable environment for investment, an effective method for detecting phishing scams is urgently needed in the blockchain ecosystem. To this end, this article proposes an approach to detect phishing scams on Ethereum by mining its transaction records. Specifically, we first crawl the labeled phishing addresses from two authorized websites and reconstruct the transaction network according to the collected transaction records. Then, by taking the transaction amount and timestamp into consideration, we propose a novel network embedding algorithm called <i>trans2vec</i> to extract the features of the addresses for subsequent phishing identification. Finally, we adopt the one-class support vector machine (SVM) to classify the nodes into normal and phishing ones. Experimental results demonstrate that the phishing detection method works effectively on Ethereum, and indicate the efficacy of <i>trans2vec</i> over existing state-of-the-art algorithms on feature extraction for transaction networks. This work is the <i>first</i> investigation on phishing detection on Ethereum via network embedding and provides insights into how features of large-scale transaction networks can be embedded.