Detecting Adversarial Examples and Other Misclassifications in Neural Networks by Introspection

Despite having excellent performances for a wide variety of tasks, modern neural networks are unable to provide a reliable confidence value allowing to detect misclassifications. This limitation is at the heart of what is known as an adversarial example, where the network provides a wrong prediction associated with a strong confidence to a slightly modified image. Moreover, this overconfidence issue has also been observed for regular errors and out-of-distribution data. We tackle this problem by what we call introspection, i.e. using the information provided by the logits of an already pretrained neural network. We show that by training a simple 3-layers neural network on top of the logit activations, we are able to detect misclassifications at a competitive level.