Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Can LLMs Find Fraudsters? Multi-level LLM Enhanced Graph Fraud Detection

Tairan Huang, Yili Wang, Qiutong Li, Changlong He, Jianliang Gao

TL;DR

A multi-level LLM enhanced framework including type-level enhancer and relation-level enhancer to enhance the difference between the fraudsters and the benign entities and enhance the ability to distinguish fraudsters is proposed.

Abstract

Graph fraud detection has garnered significant attention as Graph Neural Networks (GNNs) have proven effective in modeling complex relationships within multimodal data. However, existing graph fraud detection methods typically use preprocessed node embeddings and predefined graph structures to reveal fraudsters, which ignore the rich semantic cues contained in raw textual information. Although Large Language Models (LLMs) exhibit powerful capabilities in processing textual information, it remains a significant challenge to perform multimodal fusion of processed textual embeddings with graph structures. In this paper, we propose a \textbf{M}ulti-level \textbf{L}LM \textbf{E}nhanced Graph Fraud \textbf{D}etection framework called MLED. In MLED, we utilize LLMs to extract external knowledge from textual information to enhance graph fraud detection methods. To integrate LLMs with graph structure information and enhance the ability to distinguish fraudsters, we design a multi-level LLM enhanced framework including type-level enhancer and relation-level enhancer. One is to enhance the difference between the fraudsters and the benign entities, the other is to enhance the importance of the fraudsters in different relations. The experiments on four real-world datasets show that MLED achieves state-of-the-art performance in graph fraud detection as a generalized framework that can be applied to existing methods.

Can LLMs Find Fraudsters? Multi-level LLM Enhanced Graph Fraud Detection

TL;DR

A multi-level LLM enhanced framework including type-level enhancer and relation-level enhancer to enhance the difference between the fraudsters and the benign entities and enhance the ability to distinguish fraudsters is proposed.

Abstract

Graph fraud detection has garnered significant attention as Graph Neural Networks (GNNs) have proven effective in modeling complex relationships within multimodal data. However, existing graph fraud detection methods typically use preprocessed node embeddings and predefined graph structures to reveal fraudsters, which ignore the rich semantic cues contained in raw textual information. Although Large Language Models (LLMs) exhibit powerful capabilities in processing textual information, it remains a significant challenge to perform multimodal fusion of processed textual embeddings with graph structures. In this paper, we propose a \textbf{M}ulti-level \textbf{L}LM \textbf{E}nhanced Graph Fraud \textbf{D}etection framework called MLED. In MLED, we utilize LLMs to extract external knowledge from textual information to enhance graph fraud detection methods. To integrate LLMs with graph structure information and enhance the ability to distinguish fraudsters, we design a multi-level LLM enhanced framework including type-level enhancer and relation-level enhancer. One is to enhance the difference between the fraudsters and the benign entities, the other is to enhance the importance of the fraudsters in different relations. The experiments on four real-world datasets show that MLED achieves state-of-the-art performance in graph fraud detection as a generalized framework that can be applied to existing methods.

Paper Structure

This paper contains 19 sections, 9 equations, 7 figures, 3 tables.

Table of Contents

  1. Introduction
  2. Related Works
  3. Graph Fraud Detection
  4. Large Language Models on Graphs
  5. Methodology
  6. Preliminaries
  7. Feature Mapping Layer
  8. Type-level Enhancer
  9. Relation-level Enhancer
  10. Fraud Detection
  11. Time Complexity Analysis
  12. Experiments
  13. Experimental Setup
  14. Overall Performance
  15. Ablation Analysis
  16. ...and 4 more sections

Figures (7)

  • Figure 1: Workflow comparison. The conventional graph fraud detection methods only utilize GNNs for model training. In contrast, our framework combines textual and graph structural information through LLMs and GNNs to enhance the ability to distinguish fraudsters.
  • Figure 2: The overall framework of MLED.
  • Figure 3: An example of constructing prompts for type-level enhancer and relation-level enhancer on YelpChi dataset.
  • Figure 4: Ablation study results on various MLED variants with the SOTA method.
  • Figure 5: Efficiency analysis on the Amazon and YelpChi datasets.
  • ...and 2 more figures

Theorems & Definitions (1)

  • definition 1