Phishing Detection in Ethereum via Temporal Graph Contrastive Learning
Cong Wu, Jing Chen, Siqi Lin, Hongda Li, Ziming Zhao

TL;DR
This paper introduces PhishEye, a novel self-supervised, dynamic, heterogeneous graph contrastive learning system for detecting Ethereum phishing activities, outperforming existing static and semi-dynamic methods.
Contribution
It presents a fully dynamic, self-supervised approach that models Ethereum transactions as a heterogeneous temporal multi-graph, capturing temporal and transaction diversity for improved phishing detection.
Findings
Achieved an F1 score of 87.23% and AUC of 98.43% for phishing transaction detection.
Identified 1,803 new phishing addresses, preventing over 2 billion USD in potential losses.
Outperformed existing static and semi-dynamic methods in detection accuracy.
Abstract
Blockchain and decentralized finance have revolutionized the financial ecosystem while simultaneously exposing it to cryptocurrency phishing attacks. Existing phishing detection methods primarily rely on graph learning, but they face significant limitations. Static graph learning approaches fail to account for the temporal evolution of phishing patterns, while semi-dynamic methods, such as those combining static GNNs with LSTM, struggle to capture the irregular and bursty nature of blockchain transactions. Moreover, these methods overlook the diversity of Ethereum transactions, treating them as homogeneous graphs, and heavily rely on supervised learning, which requires extensive labeled data that is not readily available. These limitations reduce their adaptability to emerging phishing threats. In this paper, we present PhishEye, a fully dynamic self-supervised system that monitors…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
