DARCCC: Detecting Adversaries by Reconstruction from Class Conditional Capsules

11/16/2018
by   Nicholas Frosst, et al.
6

We present a simple technique that allows capsule models to detect adversarial images. In addition to being trained to classify images, the capsule model is trained to reconstruct the images from the pose parameters and identity of the correct top-level capsule. Adversarial images do not look like a typical member of the predicted class and they have much larger reconstruction errors when the reconstruction is produced from the top-level capsule for that class. We show that setting a threshold on the l2 distance between the input image and its reconstruction from the winning capsule is very effective at detecting adversarial images for three different datasets. The same technique works quite well for CNNs that have been trained to reconstruct the image from all or part of the last hidden layer before the softmax. We then explore a stronger, white-box attack that takes the reconstruction error into account. This attack is able to fool our detection technique but in order to make the model change its prediction to another class, the attack must typically make the "adversarial" image resemble images of the other class.

READ FULL TEXT

page 5

page 8

page 9

page 10

page 11

page 12

page 13

research
07/05/2019

Detecting and Diagnosing Adversarial Images with Class-Conditional Capsule Reconstructions

Adversarial examples raise questions about whether neural network models...
research
02/19/2021

Effective and Efficient Vote Attack on Capsule Networks

Standard Convolutional Neural Networks (CNNs) can be easily fooled by im...
research
10/14/2020

An Adversarial Attack against Stacked Capsule Autoencoder

Capsule network is a kind of neural network which uses spatial relations...
research
01/28/2019

CapsAttacks: Robust and Imperceptible Adversarial Attacks on Capsule Networks

Capsule Networks envision an innovative point of view about the represen...
research
08/10/2021

Correlation Clustering Reconstruction in Semi-Adversarial Models

Correlation Clustering is an important clustering problem with many appl...
research
02/21/2023

From seeing to remembering: Images with harder-to-reconstruct representations leave stronger memory traces

Much of what we remember is not due to intentional selection, but simply...
research
03/18/2019

Advanced Capsule Networks via Context Awareness

Capsule Networks (CN) offer new architectures for Deep Learning (DL) com...

Please sign up or login with your details

Forgot password? Click here to reset