/Labeled-Transactions-based-Dataset-of-Ethereum-Network

Datasets used in the paper "Labeled Transactions-based Dataset of Ethereum Network"

MIT LicenseMIT

A Labeled Transactions-Based Dataset on the Ethereum Network

Datasets used in two papers:

Abstract:

A few datasets of blockchain networks are available to be used in evaluating intrusion detection systems, and some of the proposed detection systems are evaluated as self-generated blockchain transactions’ datasets. These blockchain datasets use an unsuitable representation, which mainly depends on transaction format, and they contain non-qualified transactions’ features that lead to increased false alarm rate if the detection system is deployed in real blockchain networks. Further, due to authors’ copyright and privacy constraints, most of the existing blockchain datasets are unavailable to be used by other researchers. The paper aims to provide a benchmark dataset of transactions-based dataset of the Ethereum network for the tuning, assessing, and comparisons of any newly proposed intrusion detection system used in Blockchain networks. The proposed dataset setup is based on a real Ethereum network and ensures abnormal transaction exposure. The proposed blockchain transactions’ dataset will be publicly available and represented using a set of transactions-based features. The requirements of reliable and valid datasets have been met in the proposed transactions-based dataset to ensure its worthiness to be used by other researchers in the same field.

BLTE: Benchmark Labeled Transactions of Ethereum Network

Dataset folder has two files :

  • Dataset.SCV file has Ethereum transactions with labeld
  • fakeAddresses_unique.txt file has fake Etherum adresses
  • The final dataset in the BLTE.csv file with feature extraction. For more details read the paper in 10.1109/ACCESS.2023.3313630

Cite this paper as:

Al-E’mari S., Anbar M., Sanjalawe Y., Manickam S. (2021) A Labeled Transactions-Based Dataset on the Ethereum Network. In: Anbar M., Abdullah N., Manickam S. (eds) Advances in Cyber Security. ACeS 2020. Communications in Computer and Information Science, vol 1347. Springer, Singapore. https://doi.org/10.1007/978-981-33-6835-4_5

Y. K. Sanjalawe and S. R. Al-E’mari, "Abnormal Transactions Detection in the Ethereum Network Using Semi-Supervised Generative Adversarial Networks," in IEEE Access, vol. 11, pp. 98516-98531, 2023, doi: 10.1109/ACCESS.2023.3313630.