LatentPoison -- Adversarial Attacks On The Latent SpaceDownload PDF

15 Feb 2018 (modified: 15 Feb 2018)ICLR 2018 Conference Blind SubmissionReaders: Everyone
Abstract: Robustness and security of machine learning (ML) systems are intertwined, wherein a non-robust ML system (classifiers, regressors, etc.) can be subject to attacks using a wide variety of exploits. With the advent of scalable deep learning methodologies, a lot of emphasis has been put on the robustness of supervised, unsupervised and reinforcement learning algorithms. Here, we study the robustness of the latent space of a deep variational autoencoder (dVAE), an unsupervised generative framework, to show that it is indeed possible to perturb the latent space, flip the class predictions and keep the classification probability approximately equal before and after an attack. This means that an agent that looks at the outputs of a decoder would remain oblivious to an attack.
TL;DR: Adversarial attacks on the latent space of variational autoencoders to change the semantic meaning of inputs
Keywords: adversarial attacks, security, auto-encoder
7 Replies

Loading