Petru Hlihor

Evaluating the Robustness of Defense Mechanisms based on AutoEncoder Reconstructions against Carlini-Wagner Adversarial Attacks

2020 · Proceedings of the Northern Lights Deep Learning Workshop

Adversarial Examples represent a serious problem affecting the security of machine learning systems. In this paper we focus on a defense mechanism based on reconstructing images before classification using an autoencoder. We experiment on several …