Some Questions about the Dataset

[yinan17]

Hi Shoumik, I'm interested in the dataset in your study and have the following three questions: 1) Are there selection criteria for downloading malware data via virusshare.com? 2) Is the specific use of the malware and benign data 1:1 in your study? 3) How to use the data in the PACE Dataset?

[ShoumikSaha]

Hi,

1. For the malware dataset, we used the Virusshare website. To be specific, we used the VirusShare_00434 folder for our malware dataset.
2. Yes. Since our work was based on ML, we maintained a balanced dataset (malware and benign 1:1).
3. I have added a Python script in the dataset folder. I hope that will help you.

Let me know is you have any other questions.