Simplicial-Map Neural Networks Robust to Adversarial Examples
Open Access
- 15 January 2021
- journal article
- research article
- Published by MDPI AG in Mathematics
- Vol. 9 (2), 169
- https://doi.org/10.3390/math9020169
Abstract
Broadly speaking, an adversarial example against a classification model occurs when a small perturbation on an input data point produces a change on the output label assigned by the model. Such adversarial examples represent a weakness for the safety of neural network applications, and many different solutions have been proposed for minimizing their effects. In this paper, we propose a new approach by means of a family of neural networks called simplicial-map neural networks constructed from an Algebraic Topology perspective. Our proposal is based on three main ideas. Firstly, given a classification problem, both the input dataset and its set of one-hot labels will be endowed with simplicial complex structures, and a simplicial map between such complexes will be defined. Secondly, a neural network characterizing the classification problem will be built from such a simplicial map. Finally, by considering barycentric subdivisions of the simplicial complexes, a decision boundary will be computed to make the neural network robust to adversarial attacks of a given size.Keywords
This publication has 14 references indexed in Scilit:
- Adversarial attacks on an oblivious recommenderPublished by Association for Computing Machinery (ACM) ,2019
- Perceptual Evaluation of Adversarial Attacks for CNN-based Image ClassificationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2019
- Certified Robustness to Adversarial Examples with Differential PrivacyPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2019
- Adversarial Examples: Attacks and Defenses for Deep LearningIEEE Transactions on Neural Networks and Learning Systems, 2019
- Approximation capability of two hidden layer feedforward neural networks with fixed weightsNeurocomputing, 2018
- Geometric and Topological InferencePublished by Cambridge University Press (CUP) ,2018
- On the approximation by neural networks with bounded number of neurons in hidden layersJournal of Mathematical Analysis and Applications, 2014
- Definitions and Basic Properties of Voronoi DiagramsPublished by Wiley ,2000
- Support-vector networksMachine Learning, 1995
- Approximation capabilities of multilayer feedforward networksNeural Networks, 1991