Title
Adversarial Images for Variational Autoencoders.
Abstract
We investigate adversarial attacks for autoencoders. We propose a procedure that distorts the input image to mislead the autoencoder in reconstructing a completely different target image. We attack the internal latent representations, attempting to make the adversarial input produce an internal representation as similar as possible as the targetu0027s. We find that autoencoders are much more robust to the attack than classifiers: while some examples have tolerably small input distortion, and reasonable similarity to the target image, there is a quasi-linear trade-off between those aims. We report results on MNIST and SVHN datasets, and also test regular deterministic autoencoders, reaching similar conclusions in all cases. Finally, we show that the usual adversarial attack for classifiers, while being much easier, also presents a direct proportion between distortion on the input, and misdirection on the output. That proportionality however is hidden by the normalization of the output, which maps a linear layer into non-linear probabilities.
Year
Venue
Field
2016
arXiv: Neural and Evolutionary Computing
Autoencoder,Normalization (statistics),MNIST database,Computer science,Artificial intelligence,Distortion,Machine learning,Adversarial system
DocType
Volume
Citations 
Journal
abs/1612.00155
2
PageRank 
References 
Authors
0.38
0
3
Name
Order
Citations
PageRank
Pedro Tabacof121.39
Julia Tavares2141.36
Eduardo Valle337322.17