Enhancing Resilience of Deep Learning Networks By Means of Transferable Adversaries

Moritz Vinzent Seiler, Heike Trautmann, Pascal Kerschke

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

Abstract

Artificial neural networks in general and deep learning networks in particular established themselves as popular and powerful machine learning algorithms. While the often tremendous sizes of these networks are beneficial when solving complex tasks, the tremendous number of parameters also causes such networks to be vulnerable to malicious behavior such as adversarial perturbations. These perturbations can change a model's classification decision. Moreover, while single-step adversaries can easily be transferred from network to network, the transfer of more powerful multi-step adversaries has - usually - been rather difficult.In this work, we introduce a method for generating strong adversaries that can easily (and frequently) be transferred between different models. This method is then used to generate a large set of adversaries, based on which the effects of selected defense methods are experimentally assessed. At last, we introduce a novel, simple, yet effective approach to enhance the resilience of neural networks against adversaries and benchmark it against established defense methods. In contrast to the already existing methods, our proposed defense approach is much more efficient as it only requires a single additional forward-pass to achieve comparable performance results.
Original languageEnglish
Title of host publicationProceedings of the International Joint Conference on Neural Networks (IJCNN)
Place of PublicationGlasgow, UK
Number of pages8
DOIs
Publication statusPublished - 2020
Externally publishedYes
EventIEEE International Joint Conference on Neural Network, IJCNN 2020 - Virtual Event
Duration: 19 Jul 202024 Jul 2020

Conference

ConferenceIEEE International Joint Conference on Neural Network, IJCNN 2020
Abbreviated titleIJCNN 2020
CityVirtual Event
Period19/07/2024/07/20

Fingerprint Dive into the research topics of 'Enhancing Resilience of Deep Learning Networks By Means of Transferable Adversaries'. Together they form a unique fingerprint.

Cite this