Logo image
Back
Regularization and Sparsity for Adversarial Robustness and Stable Attribution
Book chapter   Peer reviewed

Regularization and Sparsity for Adversarial Robustness and Stable Attribution

Daniel Schwartz, Yigit Alparslan and Edward Kim
Advances in Visual Computing
07 Dec 2020
DOI: https://doi.org/10.1007/978-3-030-64556-4_1

Abstract

Adversarial attacks Artificial intelligence safety Attribution Black-box approach Image perturbation Regularization Robust machine learning Sparsity
In recent years, deep neural networks (DNNs) have had great success in machine learning and pattern recognition. It has been shown that these networks can match or exceed human-level performance in difficult image recognition tasks. However, recent research has raised a number of critical questions about the robustness and stability of these deep learning architectures. Specifically, it has been shown that they are prone to adversarial attacks, i.e. perturbations added to input images to fool the classifier, and furthermore, trained models can be highly unstable to hyperparameter changes. In this work, we craft a series of experiments with multiple deep learning architectures, varying adversarial attacks, and different class attribution methods on the CIFAR-10 dataset in order to study the effect of sparse regularization to the robustness (accuracy and stability), in deep neural networks. Our results both qualitatively show and empirically quantify the amount of protection and stability sparse representations lend to machine learning robustness in the context of adversarial examples and class attribution.

Metrics

14 Record Views
6 citations in Scopus

Details

Logo image