DeFiGuard: A Price Manipulation Detection Service in DeFi using Graph Neural Networks

TL;DR

DeFiGuard employs Graph Neural Networks to detect price manipulation attacks in DeFi, significantly improving detection accuracy and speed, thereby enhancing security for DeFi users and applications.

Contribution

This paper introduces DeFiGuard, a novel GNN-based detection service for PMA in DeFi, utilizing unique cash flow graph features for improved accuracy.

Findings

DeFiGuard outperforms baseline models in accuracy, TPR, FPR, and AUC-ROC.

Classifies transactions within less than 6 seconds, enabling timely responses.

Ablation studies confirm the effectiveness of four proposed node features.

Abstract

The prosperity of Decentralized Finance (DeFi) unveils underlying risks, with reported losses surpassing 3.2 billion USD between 2018 and 2022 due to vulnerabilities in Decentralized Applications (DApps). One significant threat is the Price Manipulation Attack (PMA) that alters asset prices during transaction execution. As a result, PMA accounts for over 50 million USD in losses. To address the urgent need for efficient PMA detection, this paper introduces a novel detection service, DeFiGuard, using Graph Neural Networks (GNNs). In this paper, we propose cash flow graphs with four distinct features, which capture the trading behaviors from transactions. Moreover, DeFiGuard integrates transaction parsing, graph construction, model training, and PMA detection. Evaluations on a dataset of 208 PMA and 2,080 non-PMA transactions show that DeFiGuard with GNN models outperforms the baseline in Accuracy, TPR, FPR, and AUC-ROC. The results of ablation studies suggest that the combination of the four proposed node features enhances DeFiGuard's efficacy. Moreover, DeFiGuard classifies transactions within 0.892 to 5.317 seconds, which provides sufficient time for the victims (DApps and users) to take action to rescue their vulnerable funds. In conclusion, this research offers a significant step towards safeguarding the DeFi landscape from PMAs using GNNs.