Deep Learning (DL) is an efficient method for botnet attack detection.
We reduce the feature dimensionality of large-scale IoT network traffic data using the dimensionality reduction techniques. Principal Component Analysis (PCA) is one of the common linear transformation methods while kernel methods, spectral methods and DL methods employ non-linear transformation techniques. Auto encoder is an unsupervised DL method that produces latent-space representation of input data at the hidden layer.
we have to implement the deep learning algorithms such as Long Short term Memory (LSTM) and Convolutional Neural Network (CNN). Finally, the experimental results shows that the performance metrics such as accuracy, precision, recall and confusion matrix.