Asymptotic Graph Neural Networks Improve Adversarial Robustness in Machine Vision

It appears your Web browser is not configured to display PDF files. Download adobe Acrobat or click here to download the PDF file.

Click here to download the PDF file.

Supplemental Files: 

Creator: 

Vertolli, Michael

Date: 

2020

Abstract: 

I propose and evaluate the first theory and computational model that explicitly describes the cognitive constraints---in the form of relational architectural constraints---that produce adversarial robustness in machine vision. This theory proposes a new form of Graph Neural Network (GNN), called an asymptotic GNN, that uses a non-linearity with a vertical asymptote to constrain where the network should be sensitive and insensitive to variations in its substructure. This approach proposes a new invariance for artificial neural networks, similar to the translational invariance of convolutional layers. I call this type of invariance ``substructure invariance'' and I show how it is capable of producing adversarial robustness in machine vision. To support these claims I first provide a detailed analysis of the two core components of the model: the asymptotic barrier function and learning branch. I then compare the asymptotic GNN to four state-of-the-art models on the MNIST dataset: one baseline and three adversarially robust models. I show that the asymptotic GNN outperforms all of the models on gradient-based adversarial attacks, mainly the DeepFool attack and the Momentum Iterative Method, and performs similar to the state-of-the-art on the decision-based PointWise attack. This establishes that the asymptotic GNN is a viable candidate for adversarial robust modeling. In subsequent analyses, I show that ablations to the core asymptotic barrier function and learning branch distinctly and differentiably impair the adversarial robustness of the asymptotic GNN. I then vary the basic structure of my model to demonstrate how the PointWise attack is symptomatic of a fundamentally different type of problem than substructure-invariance, mainly a feedback-based denoising operation.

Subject: 

Artificial Intelligence
Psychology - Cognitive

Language: 

English

Publisher: 

Carleton University

Thesis Degree Name: 

Doctor of Philosophy: 
Ph.D.

Thesis Degree Level: 

Doctoral

Thesis Degree Discipline: 

Cognitive Science

Parent Collection: 

Theses and Dissertations

Items in CURVE are protected by copyright, with all rights reserved, unless otherwise indicated. They are made available with permission from the author(s).