Usage of DikeDataset

[vanraditya]

@iosifache I would like to know how would the usage of the dataset would be, I'm dong a paper on malware classification, however the dataset value of benign.csv features are all 0. so I Conclude this would be to easy for ml models to predict, or am i using the dataset the wrong way. Please assist me regarding the matter

thank you

best regards,
vanraditya

[iosifache]

Hi Ivan,

The zero features for benign programs are documented in the README.md file here:

For the benign files, the process was straight-forward as the malice and the memberships were set to 0.

Could you clarify what you mean by "this would be to easy for ml models to predict"? I'd also appreciate if you could expand on what specific assistance you're looking for.

In the meantime, you might find it helpful to review how other researchers have approached this issue. There are over 100 papers that have successfully used DikeDataset, which may provide insights relevant to your use case.