Intrusion Detection Toward Feature Reconstruction using Huber Conditional Variational AutoEncoder

Autoencoder is recently one of the widely used machine learning approaches where the network is trained to learn the data representation. This paper considers Autoencoder for Feature Reconstruction in Intrusion Detection System. Two networks are used to form an autoencoder; the left part, an Encoder network used to learn and compress data in order to reduce feature dimension, and the right part Decoder network, which can be used to reconstruct content into its original format instead of categorizing the data. However, the ability to approximate data reconstructed to the original one in an accurate manner is still a challenging process. Thus, we propose a Conditional Variational Autoencoder with an adaptive loss function named Adaptive Huber CVAE (AH-CVAE). We replace the classical reconstruction loss function with a flexible loss function in order to minimize reconstruction error. Then, this approach is proposed to make an optimal estimation of Intrusion Detection data and achieve an accurate approximation. We conduct our experiment on two datasets, NSL-KDD and UNSW-NB15 Dataset, and compare results with other existing approaches. AH-CVAE can better approximate the original and the reconstructed feature in the intrusion detection dataset.