arXiv：cs.LG· Yuchen Lei, Yuexin Xiang, Rafael Dowsley, Tsz Hon Yuen, Andreas Deppeler, Jiangshan Yu, Qin Wang, Kim-Kwang Raymond Choo·· 4 小时前AI 评分35
大语言模型用于加密货币交易分析：以比特币为例的研究
Large Language Models for Cryptocurrency Transaction Analysis: A Bitcoin Case Study
AI 导读
研究将 LLM 应用于真实比特币交易图，并提出三层评估框架及 LLM4TG 图表示格式与 CETraS 采样算法，显著降低 token 需求。实验显示，LLM 在节点级基础信息识别准确率超 98.50%，获取有效特征比例达 95.00%，在极少标注数据下分类 top-3 准确率达 72.43% 并附带解释。
正文
Abstract:Cryptocurrencies are widely used, yet current methods for analyzing transactions often rely on opaque, black-box models. While these models may achieve high performance, their outputs are usually difficult to interpret and adapt, making it challenging to capture nuanced behavioral patterns. Large language models (LLMs) have the potential to address these gaps, but their capabilities in this area remain largely unexplored, particularly in cybercrime detection. In this paper, we test this hypothesis by applying LLMs to real-world cryptocurrency transaction graphs, with a focus on Bitcoin, one of the most studied and widely adopted blockchain networks. We introduce a three-tiered framework to assess LLM capabilities: foundational metrics, characteristic overview, and contextual interpretation. This includes a new, human-readable graph representation format, LLM4TG, and a connectivity-enhanced transaction graph sampling algorithm, CETraS. Together, they significantly reduce token requirements, transforming the analysis of multiple moderately large-scale transaction graphs with LLMs from nearly impossible to feasible under strict token limits. Experimental results demonstrate that LLMs have outstanding performance on foundational metrics and characteristic overview, where the accuracy of recognizing most basic information at the node level exceeds 98.50% and the proportion of obtaining meaningful characteristics reaches 95.00%. Regarding contextual interpretation, LLMs also demonstrate strong performance in classification tasks, even with very limited labeled data, where top-3 accuracy reaches 72.43% with explanations. While the explanations are not always fully accurate, they highlight the strong potential of LLMs in this domain. At the same time, several limitations persist, which we discuss along with directions for future research.
| Subjects: | Cryptography and Security (cs.CR); Machine Learning (cs.LG) |
| Cite as: | arXiv:2501.18158 [cs.CR] |
| (or arXiv:2501.18158v4 [cs.CR] for this version) | |
| https://doi.org/10.48550/arXiv.2501.18158 arXiv-issued DOI via DataCite |
Submission history
From: Yuexin Xiang [view email]
[v1]
Thu, 30 Jan 2025 05:48:13 UTC (17,324 KB)
[v2]
Mon, 3 Feb 2025 10:45:22 UTC (16,972 KB)
[v3]
Thu, 4 Sep 2025 07:46:37 UTC (16,903 KB)
[v4]
Tue, 6 Oct 2026 11:58:33 UTC (1,142 KB)
来源：arXiv：cs.LG · arxiv.org