However, most existing autoencoder-based methods discard the reconstruction of auxiliary information, which poses a huge challenge for better representation learning and model scalability.

The autoencoder network model for HIV classification, proposed in this paper, thus outperforms the conventional feedforward neural network models and is a much better classifier.

We propose an unsupervised method for detecting adversarial attacks in inner layers of autoencoder (AE) networks by maximizing a non-parametric measure of anomalous node activations.