# Balanced-BiEGCN: A Bidirectional EvolveGCN with a Class-Balanced Learning Network for Dynamic Anomaly Detection in Bitcoin

## TL;DR

This paper introduces a new method for detecting Bitcoin transaction anomalies by improving dynamic graph models to handle evolving patterns and class imbalance.

## Contribution

The novel Balanced-BiEGCN model introduces bidirectional temporal fusion and class-balanced learning to enhance anomaly detection in Bitcoin transactions.

## Key findings

- Balanced-BiEGCN outperforms existing methods in detecting Bitcoin transaction anomalies.
- The bidirectional temporal fusion mechanism improves capturing long-range dependencies in transaction networks.
- Class-balanced learning helps mitigate the impact of class imbalance in anomaly detection.

## Abstract

Bitcoin transaction anomaly detection is essential for maintaining financial market stability. A significant challenge is capturing the dynamically evolving transaction patterns within transaction networks. Dynamic graph models are effective for characterizing the temporal evolution of transaction systems. However, current methods struggle to mine long-range temporal dependencies and address the class imbalance caused by the scarcity of abnormal samples. To address these issues, we propose a novel approach, the Bidirectional EvolveGCN with Class-Balanced Learning Network (Balanced-BiEGCN), for Bitcoin transaction anomaly detection. This model integrates two key components: (1) a bidirectional temporal feature fusion mechanism (Bi-EvolveGCN) that enhances the capture of long-range temporal dependencies and (2) a Sample Class Transformation (CSCT) classifier that generates difficult-to-distinguish abnormal samples to balance the positive and negative class distribution. The generation of these samples is guided by two loss functions: the adjacency distance adaptive loss function and the symmetric space adjustment loss function, which optimize the spatial distribution and confusion of abnormal samples. Experimental results on the Elliptic dataset demonstrate that Balanced-BiEGCN outperforms existing baseline methods in anomaly detection.