Improving Smart Contract Security with Contrastive Learning-based Vulnerability Detection

TL;DR

This paper introduces Clear, a contrastive learning-based approach that leverages correlations among smart contracts to improve vulnerability detection, significantly outperforming existing deep learning methods on a large dataset.

Contribution

The paper proposes a novel contrastive learning framework that captures contract correlations, enhancing vulnerability detection accuracy beyond prior independent-input models.

Findings

Clear achieves the highest performance among tested methods.

F1-score improves by 9.73%-39.99% over existing approaches.

Effective utilization of contract correlations enhances detection accuracy.

Abstract

Currently, smart contract vulnerabilities (SCVs) have emerged as a major factor threatening the transaction security of blockchain. Existing state-of-the-art methods rely on deep learning to mitigate this threat. They treat each input contract as an independent entity and feed it into a deep learning model to learn vulnerability patterns by fitting vulnerability labels. It is a pity that they disregard the correlation between contracts, failing to consider the commonalities between contracts of the same type and the differences among contracts of different types. As a result, the performance of these methods falls short of the desired level. To tackle this problem, we propose a novel Contrastive Learning Enhanced Automated Recognition Approach for Smart Contract Vulnerabilities, named Clear. In particular, Clear employs a contrastive learning (CL) model to capture the fine-grained correlation information among contracts and generates correlation labels based on the relationships between contracts to guide the training process of the CL model. Finally, it combines the correlation and the semantic information of the contract to detect SCVs. Through an empirical evaluation of a large-scale real-world dataset of over 40K smart contracts and compare 13 state-of-the-art baseline methods. We show that Clear achieves (1) optimal performance over all baseline methods; (2) 9.73%-39.99% higher F1-score than existing deep learning methods.