Imperial College London
Portrait Picture

Professor Emil Lupu

Faculty of Engineering, Department of Computing

Professor of Computer Systems
 
 
 
//

Contact

 

e.c.lupu Website

 
 
//

Location

 

564Huxley BuildingSouth Kensington Campus

//

Summary

 

Publications

Citation

BibTex format

@inproceedings{Co:2021:10.1109/ICIP42928.2021.9506325,
author = {Co, KT and Muñoz-González, L and Kanthan, L and Glocker, B and Lupu, EC},
doi = {10.1109/ICIP42928.2021.9506325},
title = {Universal adversarial robustness of texture and shape-biased models},
url = {http://dx.doi.org/10.1109/ICIP42928.2021.9506325},
year = {2021}
}
Download

RIS format (EndNote, RefMan)

TY  - CPAPER
AB  - Increasing shape-bias in deep neural networks has been shown to improverobustness to common corruptions and noise. In this paper we analyze theadversarial robustness of texture and shape-biased models to UniversalAdversarial Perturbations (UAPs). We use UAPs to evaluate the robustness of DNNmodels with varying degrees of shape-based training. We find that shape-biasedmodels do not markedly improve adversarial robustness, and we show thatensembles of texture and shape-biased models can improve universal adversarialrobustness while maintaining strong performance.
AU  - Co,KT
AU  - Muñoz-González,L
AU  - Kanthan,L
AU  - Glocker,B
AU  - Lupu,EC
DO  - 10.1109/ICIP42928.2021.9506325
PY  - 2021///
TI  - Universal adversarial robustness of texture and shape-biased models
UR  - http://dx.doi.org/10.1109/ICIP42928.2021.9506325
UR  - http://arxiv.org/abs/1911.10364v3
UR  - http://hdl.handle.net/10044/1/91993
ER  -
Download