Decentralized finance (DeFi) represents a novel financial system but faces significant fraud challenges, leading to substantial losses. Recent advancements in artificial intelligence (AI) show potential for complex fraud detection. Despite growing interest, a systematic review of these methods is lacking. This survey correlates fraud types with DeFi project stages, presenting a taxonomy based on the project life cycle. We evaluate AI techniques, revealing notable findings such as the superiority of tree-based and graph-related models. Based on these insights, we offer recommendations and outline future research directions to aid researchers, practitioners, and regulators in enhancing DeFi security.

中文翻译：

---

去中心化金融中人工智能驱动的欺诈检测：项目生命周期视角


去中心化金融 （DeFi） 代表了一种新颖的金融系统，但面临重大的欺诈挑战，导致重大损失。人工智能 （AI） 的最新进展显示了复杂欺诈检测的潜力。尽管人们的兴趣日益浓厚，但缺乏对这些方法的系统评价。该调查将欺诈类型与 DeFi 项目阶段相关联，提出了基于项目生命周期的分类法。我们评估了 AI 技术，揭示了显着的发现，例如基于树和图形相关模型的优越性。基于这些见解，我们提供建议并概述未来的研究方向，以帮助研究人员、从业者和监管机构增强 DeFi 安全性。