## Track 1: Pictorial-based GAN for generating Malign Samples
The pictorial dataset is a data representation format that has shown good performance in generating artificial samples by using the GAN technique. If you choose this track, you will be required to transform the provided raw dataset into a pictorial form of your choice, use it to train the ML classifier and then extract some data items you will use to train the GAN. The comparison between the original ML model and the one trained with GAN data will be based on your chosen representation format.

## Track 2: Raw Data-based GAN for generating Malign Samples
If you choose this track, you will directly use the provided raw data to extract the seeds for the GAN training. In addition, the comparison between the baseline and model trained on GAN data will be based on this representation format.

The solutions for track 1 and 2 will be evaluated based on the accuracy on the validation set (public) and test set (private) as well as on the quality of the generated malware samples.

## Evaluation Metric
The evaluation metric for this competition is the RMSE (root mean squared error). 

## Tracks 1 and 2 Submission Format:
As given in Sample_submission.csv file

```
ID, Labels
1,0
```