IEEE Transactions on Cybernetics 2019

Learning Neural Representations for Network Anomaly Detection

IEEE Transactions on Cybernetics 2019 vanloicao/SAEDVAE

Our approach is to introduce new regularizers to a classical autoencoder (AE) and a variational AE, which force normal data into a very tight area centered at the origin in the nonsaturating area of the bottleneck unit activations.

INTRUSION DETECTION MODEL SELECTION UNSUPERVISED ANOMALY DETECTION