Context

Cryptojacking is the unauthorized use of someone else’s computer to mine cryptocurrency. The crypto-mining code works in the background as unsuspecting victims use their computers normally. The only sign they might notice is slower performance or lags in execution. Lately, the attackers have been moving their targets from personal computers to cloud servers, all thanks to server's higher computational power and many poorly configured server setups. Although many statistical methods have been designed for cryptojacking attack detection, designing a real-time detector with low computational overhead is still one of the main concerns. On the other hand, the evaluation of new detection algorithms and techniques heavily relies on the existence of well-designed datasets. This newly generated dataset is specifically targetted to analyze a server instance's performance during a crypto-jacking attack and to encourage new avenues to detect said attacks by utilizing the performance metrics.

Content

The dataset includes 3 CSV files, as described below.

1. Anormal dataset
2. Normal dataset
3. Complete dataset

Acknowledgements

I would like to thank my Education Institution, Informatics Institute of Technology, for providing me with the infrastructure required to collect this dataset.

Inspiration

This dataset is to encourage any data scientist out there to develop more ways to detect attacks based on performance data.