How to train and fit a LSTM model on an encrypted dataset

Question

I am beginner in deep learning, and I am trying to do a project on detection of encrypted malicious traffic using Long Short Term Memory (LSTM). I have the two benign and malicious data sets. What dependent do I need to import and how to train and fit the model on the dataset? Do I need to combine two dataset and train the model over it, since LSTM gets the features automatically? Any help deeply appreciated.