# VulnSense: Efficient Vulnerability Detection in Ethereum Smart Contracts by Multimodal Learning with Graph Neural Network and Language Model

arXiv: https://arxiv.org/abs/2309.08474 · HTML: https://mlsanity.com/paper/2309.08474/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 49 references that are in the map.
- First posted on arXiv 15 Sep 2023.

## Builds on (most cited first, 14 of 14)

- [Multimodal Machine Learning: A Survey and Taxonomy](https://mlsanity.com/paper/1705.09406/) (2017)
- [Multimodal Learning with Transformers: A Survey](https://mlsanity.com/paper/2206.06488/) (2022)
- [Slither: A Static Analysis Framework For Smart Contracts](https://mlsanity.com/paper/1908.09878/) (2019)
- [Securify: Practical Security Analysis of Smart Contracts](https://mlsanity.com/paper/1806.01143/) (2018)
- [Empirical Review of Automated Analysis Tools on 47,587 Ethereum Smart Contracts](https://mlsanity.com/paper/1910.10601/) (2019)
- [Combining Graph Neural Networks with Expert Knowledge for Smart Contract Vulnerability Detection](https://mlsanity.com/paper/2107.11598/) (2021)
- [ContractFuzzer: Fuzzing Smart Contracts for Vulnerability Detection](https://mlsanity.com/paper/1807.03932/) (2018)
- [A Review on Methods and Applications in Multimodal Deep Learning](https://mlsanity.com/paper/2202.09195/) (2022)
- [How Effective are Smart Contract Analysis Tools? Evaluating Smart Contract Static Analysis Tools Using Bug Injection](https://mlsanity.com/paper/2005.11613/) (2020)
- [SmartBugs: A Framework to Analyze Solidity Smart Contracts](https://mlsanity.com/paper/2007.04771/) (2020)
- [DEFECTCHECKER: Automated Smart Contract Defect Detection by Analyzing EVM Bytecode](https://mlsanity.com/paper/2009.02663/) (2020)
- [ESCORT: Ethereum Smart COntRacTs Vulnerability Detection using Deep Neural Network and Transfer Learning](https://mlsanity.com/paper/2103.12607/) (2021)
- [xFuzz: Machine Learning Guided Cross-Contract Fuzzing](https://mlsanity.com/paper/2111.12423/) (2021)
- [HyMo: Vulnerability Detection in Smart Contracts using a Novel Multi-Modal Hybrid Model](https://mlsanity.com/paper/2304.13103/) (2023)

## Built on by (most cited first, 4 of 4)

- [Vulnerability Detection in Ethereum Smart Contracts via Machine Learning: A Qualitative Analysis](https://mlsanity.com/paper/2407.18639/) (2024)
- [Vulnerability Detection in Smart Contracts: A Comprehensive Survey](https://mlsanity.com/paper/2407.07922/) (2024)
- [Robust Smart Contract Vulnerability Detection via Contrastive Learning-Enhanced Granular-ball Training](https://mlsanity.com/paper/2603.27734/) (2026)
- [Towards Secure Cloud-Native Computing: Unveiling Kubernetes Misconfigurations with Large Language Models](https://mlsanity.com/paper/2609.20834/) (2026)

## Abstract (arXiv)

This paper presents VulnSense framework, a comprehensive approach to efficiently detect vulnerabilities in Ethereum smart contracts using a multimodal learning approach on graph-based and natural language processing (NLP) models. Our proposed framework combines three types of features from smart contracts comprising source code, opcode sequences, and control flow graph (CFG) extracted from bytecode. We employ Bidirectional Encoder Representations from Transformers (BERT), Bidirectional Long Short-Term Memory (BiLSTM) and Graph Neural Network (GNN) models to extract and analyze these features. The final layer of our multimodal approach consists of a fully connected layer used to predict vulnerabilities in Ethereum smart contracts. Addressing limitations of existing vulnerability detection methods relying on single-feature or single-model deep learning techniques, our method surpasses accuracy and effectiveness constraints. We assess VulnSense using a collection of 1.769 smart contracts derived from the combination of three datasets: Curated, SolidiFI-Benchmark, and Smartbugs Wild. We then make a comparison with various unimodal and multimodal learning techniques contributed by GNN, BiLSTM and BERT architectures. The experimental outcomes demonstrate the superior performance of our proposed approach, achieving an average accuracy of 77.96% across all three categories of vulnerable smart contracts.