Adversarial Attacks on Variational Autoencoders

Abstract

Adversarial attacks are malicious inputs that derail machine-learning models. We propose a scheme to attack autoencoders, as well as a quantitative evaluation framework that correlates well with the qualitative assessment of the attacks. We assess --- with statistically validated experiments --- the resistance to attacks of three variational autoencoders (simple, convolutional, and DRAW) in three datasets (MNIST, SVHN, CelebA), showing that both DRAW's recurrence and attention mechanism lead to better resistance. As autoencoders are proposed for compressing data --- a scenario in which their safety is paramount --- we expect more attention will be given to adversarial attacks on them.

References in corpus (5)

• Auto-Encoding Variational Bayes
• Stochastic Backpropagation and Approximate Inference in Deep Generative Models
• A note on the evaluation of generative models
• Adversarial Images for Variational Autoencoders
• Adversarial examples for generative models

Cited by in corpus (11)

• Adversarial Attacks Against Deep Generative Models on Data: A Survey
• Improving VAEs' Robustness to Adversarial Attack
• Double Backpropagation for Training Autoencoders against Adversarial Attack
• Certifiably Robust Variational Autoencoders
• Towards a Theoretical Understanding of the Robustness of Variational Autoencoders
• MixDefense: A Defense-in-Depth Framework for Adversarial Example Detection Based on Statistical and Semantic Analysis
• Provably robust deep generative models
• Improving White-box Robustness of Pre-processing Defenses via Joint Adversarial Training
• Diagnosing Vulnerability of Variational Auto-Encoders to Adversarial Attacks
• A Generative Model based Adversarial Security of Deep Learning and Linear Classifier Models
• Type I Attack for Generative Models