Construction of Error Correcting Output Codes for Robust Deep Neural Networks Based on Label Grouping Scheme

Youn, Hwiyoung; Kwon, Soonhee; Lee, Hyun‐Hee; Kim, Jiho; Hong, Song‐Nam; Shin, Dong-Joon

doi:10.1109/ic-nidc54101.2021.9660486

Search citation statements

Order By: Relevance

Paper Sections

Select...

Code Design1

Citation Types

Supporting

Mentioning

Contrasting

Year Published

2023

Publication Types

Select...

Other1

Relationship

Self Cite0

Independent1

Authors

Journals

Cited by 1 publication

(1 citation statement)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The use of randomly generated codewords is well motivated since it has been demonstrated to perform well (Dietterich & Bakiri, 1991;James & Hastie, 1998;Ahmed et al, 2021). Other works that focus on codeword design for ECOC ensembles include Youn et al (2021) and Gupta & Amin (2021).…”

Section: Code Designmentioning

confidence: 99%

Improved Robustness Against Adaptive Attacks With Ensembles and Error-Correcting Output Codes

Philippon¹,

Gagné²

2023

Preprint

View full text Add to dashboard Cite

Neural network ensembles have been studied extensively in the context of adversarial robustness and most ensemble-based approaches remain vulnerable to adaptive attacks. In this paper, we investigate the robustness of Error-Correcting Output Codes (ECOC) ensembles through architectural improvements and ensemble diversity promotion. We perform a comprehensive robustness assessment against adaptive attacks and investigate the relationship between ensemble diversity and robustness. Our results demonstrate the benefits of ECOC ensembles for adversarial robustness compared to regular ensembles of convolutional neural networks (CNNs) and show why the robustness of previous implementations is limited. We also propose an adversarial training method specific to ECOC ensembles that allows to further improve robustness to adaptive attacks.

show abstract