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.

A transfer-learned hierarchical variational autoencoder model for computational design of anticancer peptides. Authors: Farzad Midjani, Hossein Abbasi, Mahdi Malekpour, Shahin Yaghoobi, Sina Abdous, ...