Enhancing Adversarial Robustness via Test-time Transformation Ensembling
Type
Conference PaperAuthors
Perez, Juan C.Alfarra, Motasem
Jeanneret, Guillaume
Rueda, Laura
Thabet, Ali Kassem

Ghanem, Bernard

Arbelaez, Pablo
KAUST Department
Computer, Electrical and Mathematical Science and Engineering (CEMSE) DivisionElectrical and Computer Engineering
Electrical and Computer Engineering Program
GCR - Award Administration
Integrative Activities
Office of Competitive Research Funds
VCC Analytics Research Group
Visual Computing Center (VCC)
Date
2021-10Permanent link to this record
http://hdl.handle.net/10754/670356
Metadata
Show full item recordAbstract
Deep learning models are prone to being fooled by imperceptible perturbations known as adversarial attacks. In this work, we study how equipping models with Test-time Transformation Ensembling (TTE) can work as a reliable defense against such attacks. While transforming the input data, both at train and test times, is known to enhance model performance, its effects on adversarial robustness have not been studied. Here, we present a comprehensive empirical study of the impact of TTE, in the form of widely-used image transforms, on adversarial robustness. We show that TTE consistently improves model robustness against a variety of powerful attacks without any need for re-training, and that this improvement comes at virtually no trade-off with accuracy on clean samples. Finally, we show that the benefits of TTE transfer even to the certified robustness domain, in which TTE provides sizable and consistent improvements.Citation
Perez, J. C., Alfarra, M., Jeanneret, G., Rueda, L., Thabet, A., Ghanem, B., & Arbelaez, P. (2021). Enhancing Adversarial Robustness via Test-time Transformation Ensembling. 2021 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW). doi:10.1109/iccvw54120.2021.00015Sponsors
This work was partially supported by the King Abdullah University of Science and Technology (KAUST) Office of Sponsored Research.Publisher
IEEEConference/Event name
18th IEEE/CVF International Conference on Computer Vision Workshops, ICCVW 2021ISBN
9781665401913arXiv
2107.14110Additional Links
https://ieeexplore.ieee.org/document/9607771/ae974a485f413a2113503eed53cd6c53
10.1109/iccvw54120.2021.00015