Bummer! This is just a preview. You need to be signed in with an account to view the entire instruction.

Well done!

You have completed (UPI) Chapter 19: AI in Cybersecurity!

Instruction

19.4.1 Dataset

We use a published framework to collect samples. Our dataset consists of files collected from three major sources: VirusShare , Maltrieve, and private collections. These origins offer a wide and multiplex amount of files for validation. Our final dataset contains 90,000 samples with 72,317 labeled as malicious and 17,683 labeled as benign. We train our model on 60,000 of the collected samples....