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

Adriana Watson; Grant Richards; Daniel Schiff

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

Computational Engineering, Finance, and Science 2025-12-12 v2 Artificial Intelligence Cryptography and Security

Authors: Adriana Watson , Grant Richards , Daniel Schiff

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.

Keywords

blockchain and cryptocurrency

Cite

@article{arxiv.2506.14933,
  title  = {Explain First, Trust Later: LLM-Augmented Explanations for Graph-Based Crypto Anomaly Detection},
  author = {Adriana Watson and Grant Richards and Daniel Schiff},
  journal= {arXiv preprint arXiv:2506.14933},
  year   = {2025}
}

Comments

11 pages, 5 figures. Code available at: https://github.com/awatson246/crypto-anomaly-detection-policy

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

Abstract

Keywords

Cite

Comments

Related papers