Explain First, Trust Later: LLM-Augmented Explanations for Graph-Based Crypto Anomaly Detection

2025/06/17 by Watson, Adriana, Richards, Grant, Schiff, Daniel · 1 citation
Computer Science · Decision Sciences · #68T07 #68T09 (Primary) 05C82 #94A60 (Secondary) #Artificial Intelligence (cs.AI) #Big Data and Digital Economy #Computational Engineering #Cryptography and Security (cs.CR) #Data Quality and Management #FOS: Computer and information sciences #Finance #G.2.2 #H.2.8 #I.2.6 #I.2.7 #K.4.4 #Scientific Computing and Data Management #and Science (cs.CE)

paper · pdf · doi:10.48550/arxiv.2506.14933

openalex publication_date 2025/06/17 · openalex created_date 2025/10/19 · openalex updated_date 2026/07/28

Abstract

The decentralized finance (DeFi) community has grown rapidly in recent years, pushed forward by cryptocurrency enthusiasts interested in the vast untapped potential of new markets. The surge in popularity of cryptocurrency has ushered in a new era of financial crime. Unfortunately, the novelty of the technology makes the task of catching and prosecuting offenders particularly challenging. Thus, it is necessary to implement automated detection tools related to policies to address the growing criminality in the cryptocurrency realm.

Citations

• From Nodes to Narratives: Explaining Graph Neural Networks with LLMs and Graph Context
• XAI meets LLMs: A Survey of the Relation between Explainable AI and Large Language Models
• LLMs for XAI: Future Directions for Explaining Explanations
• Usable XAI: 10 Strategies Towards Exploiting Explainability in the LLM Era
• Detecting Anomalies in Blockchain Transactions using Machine Learning Classifiers and Explainability Analysis
• Enhancing Illicit Activity Detection using XAI: A Multimodal Graph-LLM Framework
• GuiltyWalker: Distance to illicit nodes in the Bitcoin network
• GraphLIME: Local Interpretable Model Explanations for Graph Neural Networks
• Anti-Money Laundering in Bitcoin: Experimenting with Graph Convolutional Networks for Financial Forensics

Cited by

• Human-Centered LLM-Agent System for Detecting Anomalous Digital Asset Transactions
• Blockchain Data Analytics: A Scoping Literature Review and Directions for Future Research

Related

• Detecting Anomalous Cryptocurrency Transactions: an AML/CFT Application of Machine Learning-based Forensics
• Anti-Money Laundering in Bitcoin: Experimenting with Graph Convolutional Networks for Financial Forensics
• Dynamic Fraud Detection: Integrating Reinforcement Learning into Graph Neural Networks
• GuiltyWalker: Distance to illicit nodes in the Bitcoin network
• Leveraging Machine Learning for Multichain DeFi Fraud Detection