Temporal Motif-aware Graph Test-time Adaptation for OOD Blockchain Anomaly Detection

2026-05-28

AI Summary

This work addresses the challenges of out-of-distribution (OOD) anomaly detection in blockchain transactions, which arise from adversarial pattern evolution driven by malicious activities and semantic discrepancies across transaction types. To tackle these issues, the paper proposes a novel approach that integrates temporal three-node motif distribution modeling with graph test-time adaptation (TTA). This method uniquely combines temporal motif-aware feature extraction from active addresses with adaptive alignment of shared structural patterns between training and test graphs, thereby effectively capturing complex anomalous transaction behaviors. Evaluated on five real-world blockchain datasets, the proposed approach achieves an average performance improvement of 54.88% over state-of-the-art graph-based anomaly detection methods. Its efficacy and robustness are further substantiated through interpretable motif case studies.

Abstract

Ever-evolving transaction patterns have significantly hindered anomaly detection on emerging cryptocurrency blockchains due to the vast number of addresses and diverse anomalous behaviors. Recently, advanced Graph Anomaly Detection (GAD) approaches applied to blockchains have faced two critical challenges: \textit{adversarial pattern evolution by malicious actors} and \textit{the out-of-distribution (OOD) problem caused by varied transaction semantics on blockchains}. To address these challenges, we propose a novel framework termed \textbf{TE}mporal \textbf{M}otif-aware \textbf{G}raph \textbf{T}est-\textbf{T}ime \textbf{A}daptation (\textbf{TEMG-TTA}). First, we comprehensively capture the 3-node temporal motif distribution of each active address using an efficient computational mechanism, enabling downstream temporal motif-aware graph learning. Second, we design a simple yet effective test-time adaptation strategy to facilitate the sharing of common patterns between training and testing graphs. Extensive experiments on 5 real-world datasets demonstrate that our proposed \textbf{TEMG-TTA} outperforms \textit{state-of-the-art} GAD approaches by an average of 54.88\%. A further case study on interpretable motif patterns reveals that \textbf{TEMG-TTA} explicitly characterizes the complex transaction patterns of anomalous addresses, thereby verifying the effectiveness of our technical designs. Our code will be made publicly available https://github.com/LuoXishuang0712/TEMG-TTA/.

Problem

• Out-of-Distribution (OOD)
• Blockchain Anomaly Detection
• Adversarial Pattern Evolution
• Temporal Motifs
• Graph Anomaly Detection

Innovation

• Temporal Motif
• Test-time Adaptation
• Graph Anomaly Detection
• Out-of-Distribution
• Blockchain