Cryptocurrency Malware Dataset – 2020
Introduction:
In recent years, cryptocurrency trades have increased dramatically, and this trend has attracted cyber-threat actors to exploit the existing vulnerabilities and infect their targets. The malicious actors use cryptocurrency malware to perform complex computational tasks using infected devices. Since cryptocurrency malware threats perform a legal process, it is a challenging task to detect this type of threat by a manual or heuristic method. In recent years, machine learning (ML) based malware threat detection solutions have obtained promising results in everyday malware hunting tasks.
In an effort to enable and facilitate the process of malware detection, the following dataset has been developed and targets MS Windows cryptocurrency malware threats since a considerable number of users use the MS Windows OS platform for trading cryptocurrencies.
Dataset Details:
This dataset provides over 700 samples, 500 of which are real-world cryptocurrency malware samples, which can be executed on the MS Windows OS platform as a portable executable file from VirusTotal and Virus Share. This dataset was collected in the following two different tracks (all samples were initially unpacked and then decompiled using the Object-dump tool):
- Malware samples (500 malware files)
- Benign samples (200 benign files)
For benign sample collection, MS Windows Crypto-wallet and Crypto-miner applications were chosen from legitimate sources, including the Microsoft Store and Coinmarketcap website (https://coinmarketcap.com). It was confirmed that these sources include all active cryptocurrencies.
The collected dataset also consists of 1571 features per dataset sample. Therefore, when working with this, it is important to note the curse of dimensionality.
Citation:
Plain Text:
Yazdinejad, A., HaddadPajouh, H., Dehghantanha, A., Parizi, R. M., Srivastava, G., & Chen, M. Y. (2020). Cryptocurrency malware hunting: A deep recurrent neural network approach. Applied Soft Computing, 96, 106630.
BibText:
@article{yazdinejad2020cryptocurrency, title={Cryptocurrency malware hunting: A deep recurrent neural network approach}, author={Yazdinejad, Abbas and HaddadPajouh, Hamed and Dehghantanha, Ali and Parizi, Reza M and Srivastava, Gautam and Chen, Mu-Yen}, journal={Applied Soft Computing}, volume={96}, pages={106630}, year={2020}, publisher={Elsevier}}
Download dataset: https://github.com/CyberScienceLab/Our-Datasets/tree/master/CryptoMalware