UniDetect: LLM-Driven Universal Fraud Detection across Heterogeneous Blockchains

2026-04-14

AI Summary

This study addresses the challenge posed by cross-chain interoperability, which facilitates the covert movement of illicit funds across heterogeneous blockchains and undermines existing single-chain regulatory mechanisms. To tackle this issue, the authors propose a novel multimodal joint reasoning framework that integrates large language models (LLMs) with transaction graphs. The approach leverages LLMs to generate universal multi-chain transaction summaries and combines them with graph-structured data through a dynamic two-stage alternating training strategy for fraudulent account detection. A key innovation is the introduction of a generalizable textual evidence generation mechanism that enables zero-shot cross-chain transfer. Experimental results demonstrate that the method outperforms state-of-the-art approaches by 5.57%–7.58% in KS score on multi-chain data, achieves over 94.58% accuracy in zero-shot cross-chain fraud detection, and improves F1 score by 6.06% on non-blockchain datasets.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Natural Language Processing: Language Grounding & Multi-modal NLP
• Computer Vision: Multi-modal Vision

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Web Mining and Content Analysis: Mining multimedia, multimodal, multilingual, cross-lingual Web data
• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG

Abstract

As cross-chain interoperability advances, decentralized finance (DeFi) protocols enable illicit funds to be reorganized into uniform liquid assets that flow throughout the cryptocurrency market. Such operations can bypass monitoring targeted at individual blockchains and thereby weaken current regulatory frameworks. Motivated by these, we introduce UniDetect, a multi-chain cryptocurrency fraud account detection method based on large language models (LLMs). Specifically, we use domain knowledge to guide the LLM to generate general transaction summary texts applicable to heterogeneous blockchain accounts, which serve as evidence for fraud account detection. Furthermore, we introduce a two-stage alternating training strategy to continuously and dynamically enhance the multimodal joint reasoning for detecting fraudulent accounts based on both the textual evidence and the transaction graph patterns. Experiments on multiple blockchains show that UniDetect outperforms existing methods 5.57% to 7.58% in Kolmogorov-Smirnov (KS). For cross-chain zero-shot detection, UniDetect identifies over 94.58% of fraudulent accounts. It also generalizes well to non-blockchain data, delivering a 6.06% improvement in F1 over existing methods. The dataset and source code are available at https://github.com/msy0513/UniDetect.

Problem

• cross-chain fraud
• heterogeneous blockchains
• DeFi illicit funds
• universal fraud detection
• regulatory bypass

Innovation

• LLM-driven fraud detection
• cross-chain interoperability
• transaction summarization
• multimodal joint reasoning
• zero-shot detection