arXiv Analytics

Sign in

arXiv:1711.02879 [cs.LG]AbstractReferencesReviewsResources

LatentPoison - Adversarial Attacks On The Latent Space

Antonia Creswell, Anil A. Bharath, Biswa Sengupta

Published 2017-11-08Version 1

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.

Comments: Submitted to ICLR 2018
Categories: cs.LG, cs.CR
Related articles: Most relevant | Search more
arXiv:2006.06861 [cs.LG] (Published 2020-06-11)
Robustness to Adversarial Attacks in Learning-Enabled Controllers
arXiv:1909.08072 [cs.LG] (Published 2019-09-17)
Adversarial Attacks and Defenses in Images, Graphs and Text: A Review
arXiv:2006.15632 [cs.LG] (Published 2020-06-28)
FDA3 : Federated Defense Against Adversarial Attacks for Cloud-Based IIoT Applications