This work proposes a new robust method for identifying abnormal contract accounts over the Ethereum network data. This method comprises hybrid features set by integrating opcode n-grams, data behavior, and term frequency-inverse document frequency source code features to train an ensemble classifier. This classifier ensemble the extra-trees and gradient boosting algorithms based on weighted soft voting to create an ensemble classifier that balances the weaknesses of individual classifiers in a given dataset. The abnormal and normal contract data are collected by analyzing the open source etherscan.io, and the problem of the imbalanced dataset is solved by performing the adaptive synthetic sampling.
Note: Due to huge volume of the dataset, the link of our dataset generated during the current study is available at: https://drive.google.com/u/1/uc?export=download&confirm=hPyP&id=1izK9Sm5yfwq3Ck9f71SUXAL41GVKQFBS
Citation Request:
Aljofey, Ali, Abdur Rasool, Qingshan Jiang, and Qiang Qu. 2022. "A Feature-Based Robust Method for Abnormal Contracts Detection in Ethereum Blockchain" Electronics 11, no. 18: 2937. https://doi.org/10.3390/electronics11182937.