UniDetect: LLM-Driven Universal Fraud Detection across Heterogeneous Blockchains

TL;DR

UniDetect leverages large language models and a novel training strategy to detect fraudulent accounts across multiple blockchains, outperforming existing methods and generalizing well to non-blockchain data.

Contribution

The paper introduces a multi-chain fraud detection method using LLM-guided transaction summaries and a two-stage training strategy for improved multimodal reasoning.

Findings

Outperforms existing methods by 5.57% to 7.58% in KS.

Identifies over 94.58% of fraudulent accounts in cross-chain zero-shot detection.

Achieves a 6.06% F1 score improvement on non-blockchain data.

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.