Reentrancy Vulnerability Detection in Smart Contracts Based on Adversarial Examples

Abstract

Reentrancy Vulnerabilities (RVs) in smart contracts pose severe financial risks to blockchain systems. While deep learning-based detection methods have shown promise, they suffer from critical limitations: (1) vulnerability to adversarial examples, (2) inadequate handling of Cross-Function RVs (CFRVs), and (3) reliance on limited training data. To address these challenges, we present SCAEG, the first adversarial example generation framework specifically designed for RV detection. SCAEG introduces five novel perturbation actions that preserve code functionality while exposing model vulnerabilities, including targeted modifications for CFRV scenarios. Our comprehensive evaluation demonstrates that SCAEG-generated examples sig nificantly degrade the performance of state-of-the-art detectors (e.g., reducing AWDNN's accuracy by 27.51 percentage points), exposing their fragility to adversarial attacks. Building on these insights, we propose VoteRD, an ensemble detection model that combines semantic, rule-based, and positional features through a multi-model voting mechanism. Experimental results show VoteRD achieves superior robustness, outperforming existing approaches by 3.7% in recall and 7.4% in F1-score (compare with AWDNN), while effectively detecting both traditional RVs and CFRVs. This work not only advances RV detection capabilities but also establishes a new benchmark for evaluating model robustness in smart contract security analysis. SCAEG and VoteRD form a synergistic framework: SCAEG systematically evaluates model robustness, while VoteRD leverages adversarial insights to enhance detection accuracy. Our datasets and tools are publicly released to support future research in adversarial testing and vulnerability detection.