Need help in research writing in field of Deep learning(GAN, CNN) and help in presentation

I need help in making a PPT and write a report on defense against adversarial attacks. This is an academic project(mtech) so I need new approach for presentation. No need to implement the project just suggest me a new approach. I have thought a few approachs but not sure weather they are correct or not. It is difficult to explain all here. we'll have google meetings. adversarial attacks : There are several attacks possible on deep learning classifiers(for example, Lets say there is a handwritten image of 5 the deep learning classifier(here I used CNN) may classify it as 6 or any other number based on attack). There are few defense methods proposed against these attacks like (bit depth reduction, Defense GAN, PixelCNN, Image quilting, Randomized diversification).