Tracking phishing on Ethereum: Transaction network embedding approach for accounts representation learning
Tracking phishing on Ethereum: Transaction network embedding approach for accounts representation learning
复制标题
DOI：
10.1016/j.cose.2023.103479
复制
发表时间：
2023-09
期刊：
影响因子：
--
通讯作者：
Zhutian Lin;Xi Xiao;Guangwu Hu;Qing Li;Bin Zhang;Xiapu Luo
中科院分区：
文献类型：
--
作者：
Zhutian Lin;Xi Xiao;Guangwu Hu;Qing Li;Bin Zhang;Xiapu Luo
以太坊的交易量一直在逐年增长，不幸的是，这伴随着网络钓鱼诈骗造成的重大损失。为了增强下游分类器更有效地区分钓鱼账户的能力，我们利用交易网络拓扑和相关的统计特征，在潜在空间中生成以太坊账户的密集表示。然而，从稀疏但大量的交易记录中学习表示的任务提出了一个重大的挑战。为了解决这个问题，我们引入了基于时间的序列发生器（TSG）和基于异质性的序列发生器（HSG）。这些生成器从交易网络中创建序列，优化交易时间约束、不同账户类型和交易金额的使用。我们的方法旨在捕捉潜在的高阶信息，并使用网络嵌入技术生成密集的向量。此外，我们提出了一种新的基于统计的采样（SBS）方法，以减轻标签泄漏。我们通过各种经典的下游分类器的实验验证了我们的方法，证明了Phish2vec在性能上优于其他比较方法，并且具有鲁棒性和稳定性。
The transaction volume of Ethereum has been witnessing a year-on-year increase, which has unfortunately been accompanied by significant losses due to phishing scams. To enhance the ability of downstream classifiers to distinguish phishing accounts more effectively, we produce dense representations of Ethereum accounts in latent space, leveraging the transaction network topology and associated statistical features. However, the task of learning representations from sparse yet voluminous transaction records presents a significant challenge. To address this, we introduce the Temporal-based Sequences Generator (TSG) and the Heterogeneous-based Sequences Generator (HSG). These generators create sequences from the transaction network, optimizing the use of transaction temporal constraints, diverse account types, and transaction amounts. Our method aims to capture latent higher-order information and generate dense vectors using a network embedding technique. Furthermore, we propose a novel Statistics-Based Sampling (SBS) method to mitigate label leakage. We validate our approach through experiments with various classic downstream classifiers, demonstrating thatPhish2vecsurpasses other comparative methods in performance and exhibits robustness and stability.