研究人员开发了一种利用时空图神经网络（GNNs）检测加密货币市场欺诈的新方法。该方法通过将市场数据表示为图来捕捉操纵计划的协调性质，从而超越了对单个交易的分析。所提出的GNN架构结合了基于注意力的空间聚合和时间Transformer编码，在真实世界的“拉高出货”计划数据集上，与传统的机器学习基线相比，表现出显著的改进。 AI
影响 引入了一种基于图的GNN方法来检测协调的市场操纵，有可能改进金融市场的欺诈检测。
排序理由 这是一篇研究论文，详细介绍了使用GNN进行欺诈检测的新方法。
AI 生成摘要 · Google Gemini · 来自 3 个来源。 我们如何撰写摘要 →
arXiv:2604.24590v1 Announce Type: new Abstract: Technological advancements in cryptocurrency markets have increased accessibility for investors, but concurrently exposed them to the risks of market manipulations. Existing fraud detection mechanisms typically rely on machine learn…
Technological advancements in cryptocurrency markets have increased accessibility for investors, but concurrently exposed them to the risks of market manipulations. Existing fraud detection mechanisms typically rely on machine learning methods that treat each financial asset (i.e…
Technological advancements in cryptocurrency markets have increased accessibility for investors, but concurrently exposed them to the risks of market manipulations. Existing fraud detection mechanisms typically rely on machine learning methods that treat each financial asset (i.e…