GMVD: smart contract vulnerability detection based on GAT-Mamba framework
Abstract
Smart contracts hold billions of dollars worth of digital currencies, and hacking attacks can not only cause users to lose their assets but also destabilize the blockchain ecosystem. Vulnerability detection in smart contracts remains a major challenge in blockchain security. Existing methods typically rely on a fixed expert mode, which leads to low accuracy. Moreover, GNN-based models fail to effectively differentiate the significance of various interaction information, while transformer models suffer from high computational complexity. To solve this problem, we propose the GAT-Mamba framework, named GMVD, to perform the smart contract vulnerability detection task. The approach first extracts expert-defined vulnerability patterns from smart contract functions. Then, the graph features are extracted by GAT. Finally, Mamba is used to model the high-dimensional vector expression of expert mode features to improve the calculation efficiency of the model. Experimental results on three common vulnerabilities, reentrancy, timestamp dependency, and infinite loop, demonstrate that our framework significantly outperforms existing cutting-edge technologies. Specifically, our method achieves 94.29 ± 0.22% accuracy in detecting reentrancy, 93.71 ± 0.24% in timestamp dependency, and 82.49 ± 0.19% in infinite loop detection.
Versions
Related
- Association between social network support and smart health device ownership among older adults: Potential parallel mediating pathways through internet use and utilization of family doctor contract services
- Hybrid deep learning–driven explainable AI framework for fault detection and classification in smart power grids
- Mamba-enhanced RT-DETR for ship detection in optical remote sensing images
- HIFN-Mamba: hybrid information flow networks with selective state-space sequence modeling for intrusion detection in the Internet of Medical Things
- Boundary-interior ratio: a spatially decomposed evaluation framework for CNN and mamba-based breast ultrasound segmentation
BibTeX
@article{liu2026gmvd,
title = {{GMVD: smart contract vulnerability detection based on GAT-Mamba framework}},
author = {Mingyan Liu and Changli Zhang},
journal = {Scientific Reports},
year = {2026},
month = oct,
doi = {10.1038/s41598-026-70582-7},
url = {https://www.nature.com/articles/s41598-026-70582-7},
note = {CC BY-NC-ND 4.0},
}
RIS
TY - JOUR
TI - GMVD: smart contract vulnerability detection based on GAT-Mamba framework
AU - Mingyan Liu
AU - Changli Zhang
PY - 2026
DA - 2026/10/05
JO - Scientific Reports
DO - 10.1038/s41598-026-70582-7
UR - https://www.nature.com/articles/s41598-026-70582-7
AB - Smart contracts hold billions of dollars worth of digital currencies, and hacking attacks can not only cause users to lose their assets but also destabilize the blockchain ecosystem. Vulnerability detection in smart contracts remains a major challenge in blockchain security. Existing methods typically rely on a fixed expert mode, which leads to low accuracy. Moreover, GNN-based models fail to effectively differentiate the significance of various interaction information, while transformer models suffer from high computational complexity. To solve this problem, we propose the GAT-Mamba framework, named GMVD, to perform the smart contract vulnerability detection task. The approach first extracts expert-defined vulnerability patterns from smart contract functions. Then, the graph features are extracted by GAT. Finally, Mamba is used to model the high-dimensional vector expression of expert mode features to improve the calculation efficiency of the model. Experimental results on three common vulnerabilities, reentrancy, timestamp dependency, and infinite loop, demonstrate that our framework significantly outperforms existing cutting-edge technologies. Specifically, our method achieves 94.29 ± 0.22% accuracy in detecting reentrancy, 93.71 ± 0.24% in timestamp dependency, and 82.49 ± 0.19% in infinite loop detection.
SN - 2045-2322
ER -