EFEVD: Enhanced Feature Extraction for Smart Contract Vulnerability Detection

Authors: Chi Jiang, Xihan Liu, Shenao Wang, Jinzhuo Liu, Yin Zhang

IJCAI 2024 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental The experimental results verify that the proposed approach significantly outperforms the state-of-the-art methods in terms of accuracy, recall, precision, and F1-score.
Researcher Affiliation Academia 1University of Electronic Science and Technology of China 2Yunnan University {chijiang, xihanliu, shenaowang}@std.uestc.edu.cn, jinzhuo.liu@hotmail.com, zhangyin123@uestc.edu.cn
Pseudocode No No pseudocode or algorithm blocks are explicitly presented in the paper.
Open Source Code Yes Our data and code are available on Git Hub1. 1https://github.com/xawmx/MTLContractdetection
Open Datasets No The dataset used in this paper comes from a realworld smart contract dataset on Ethereum. The paper describes the dataset and its properties, but does not provide a specific link, DOI, repository, or formal citation for public access to the dataset itself.
Dataset Splits No The overall dataset is divided into a train set and a test set at a ratio of 7:3, where the train set is used for model training and the test set is used for model performance evaluations. A validation set is not explicitly mentioned.
Hardware Specification Yes All the models are trained using an NVIDIA Ge Force RTX 3060 GPU and implemented with Tensor Flow 1.15.
Software Dependencies Yes All the models are trained using an NVIDIA Ge Force RTX 3060 GPU and implemented with Tensor Flow 1.15.
Experiment Setup Yes The batch size is set to 64, and the learning rate is initialized to 0.01 and is dynamic during training. The epoch hyperparameter in this paper is set to 30.