Adversarial Examples Detection and Analysis with Layer-wise Autoencoders

Understand

We present a mechanism for detecting adversarial examples based on data representations taken from the hidden layers of the target network.

• For this purpose, we train individual autoencoders at intermediate layers of the target network.
• This allows us to describe the manifold of true data and, in consequence, decide whether a given example has the same characteristics as true data.
• It also gives us insight into the behavior of adversarial examples and their flow through the layers of a deep neural network.