一句话：提出 ScamSweeper 框架，利用交易图在大规模 Ethereum 数据上检测 Web3 诈骗与钓鱼账户，性能超越现有方法。
Web3 应用尤其是 Ethereum 平台近年快速增长，也成为诈骗目标。诈骗者模仿合法平台服务与常规活动来欺骗用户。现有钓鱼账户检测工具依赖图学习或采样算法获取图特征，但大规模且带时间属性的交易网络呈幂律分布，给 Web3 诈骗检测带来挑战。本文提出 ScamSweeper，一个在 Ethereum 上识别 Web3 诈骗的新框架，并收集了包含 Web3 诈骗、钓鱼和正常账户的大规模交易数据集。实验表明，ScamSweeper 在检测 Web3 诈骗方面超过当前最优方法。
The web3 applications have recently been growing, especially on the Ethereum platform, starting to become the target of scammers. The web3 scams, imitating the services provided by legitimate platforms, mimic regular activity to deceive users. The current phishing account detection tools utilize graph learning or sampling algorithms to obtain graph features. However, large-scale transaction networks with temporal attributes conform to a power-law distribution, posing challenges in detecting web3 scams. In this paper, we present ScamSweeper, a novel framework to identify web3 scams on Ethereum. Furthermore, we collect a large-scale transaction dataset consisting of web3 scams, phishing, and normal accounts. Our experiments indicate that ScamSweeper exceeds the state-of-the-art in detecting web3 scams.CCS Concepts• Security and privacy → Software security engineering