Anomaly Detection of Adversarial Examples using Class-conditional Generative Adversarial Networks. (arXiv:2105.10101v2 [cs.LG] UPDATED)

Deep Neural Networks (DNNs) have been shown vulnerable to Test-Time Evasion
attacks (TTEs, or adversarial examples), which, by making small changes to the
input, alter the DNN's decision. We propose an unsupervised attack detector on
DNN classifiers based on class-conditional Generative Adversarial Networks
(GANs). We model the distribution of clean data conditioned on the predicted
class label by an Auxiliary Classifier GAN (AC-GAN). Given a test sample and
its predicted class, three detection statistics are calculated based on the
AC-GAN …

anomaly anomaly detection arxiv detection examples generative adversarial networks networks