Relationship between Model Compression and Adversarial Robustness: A Review of Current Evidence

Increasing the model capacity is a known approach to enhance the adversarial robustness of deep learning networks. On the other hand, various model compression techniques, including pruning and quantization, can reduce the size of the network while preserving its accuracy. Several recent studies hav...

Full description

Saved in:
Bibliographic Details
Published inarXiv.org
Main Authors Pavlitska, Svetlana, Grolig, Hannes, Zöllner, J Marius
Format Paper
LanguageEnglish
Published Ithaca Cornell University Library, arXiv.org 27.11.2023
Subjects
Robustness
Online AccessGet full text

Cover

More Information
Summary:Increasing the model capacity is a known approach to enhance the adversarial robustness of deep learning networks. On the other hand, various model compression techniques, including pruning and quantization, can reduce the size of the network while preserving its accuracy. Several recent studies have addressed the relationship between model compression and adversarial robustness, while some experiments have reported contradictory results. This work summarizes available evidence and discusses possible explanations for the observed effects.
ISSN:2331-8422