Robustness against Adversarial Attacks in Neural Networks using Incremental Dissipativity release_rslbawn5avc5hmyieq3o5odjcu

by Bernardo Aquino, Arash Rahnama, Peter Seiler, Lizhen Lin, Vijay Gupta

Released as a article .

2022  

Abstract

Adversarial examples can easily degrade the classification performance in neural networks. Empirical methods for promoting robustness to such examples have been proposed, but often lack both analytical insights and formal guarantees. Recently, some robustness certificates have appeared in the literature based on system theoretic notions. This work proposes an incremental dissipativity-based robustness certificate for neural networks in the form of a linear matrix inequality for each layer. We also propose an equivalent spectral norm bound for this certificate which is scalable to neural networks with multiple layers. We demonstrate the improved performance against adversarial attacks on a feed-forward neural network trained on MNIST and an Alexnet trained using CIFAR-10.
In text/plain format

Archived Files and Locations

application/pdf  183.4 kB
file_25aakyaeczelvhxbrxcpzcw53u
arxiv.org (repository)
web.archive.org (webarchive)
Read Archived PDF
Preserved and Accessible
Type  article
Stage   submitted
Date   2022-02-14
Version   v2
Language   en ?
arXiv  2111.12906v2
Work Entity
access all versions, variants, and formats of this works (eg, pre-prints)
Catalog Record
Revision: f631025c-43a9-4b84-9930-6c85e5304962
API URL: JSON