Blind Adversarial Training: Balance Accuracy and Robustness.

scholar.google.com › citations

… adversarial training: Balance accuracy and robustness
Xie · Cited by 7

Blind Adversarial Training: Balance Accuracy and Robustness - arXiv

Apr 10, 2020 · This paper proposes a novel AT approach named blind adversarial training (BAT) to better balance the accuracy and robustness.

[2004.05914] Blind Adversarial Training: Balance Accuracy and ...

ar5iv.labs.arxiv.org › abs

Adversarial training (AT) aims to improve the robustness of deep learning models by mixing clean data and adversarial examples (AEs).

Blind Adversarial Training: Balance Accuracy and Robustness ...

www.researchgate.net › ... › Robustness

Adversarial training (AT) aims to improve the robustness of deep learning models by mixing clean data and adversarial examples (AEs).

(PDF) Blind Adversarial Pruning: Balance Accuracy, Efficiency and ...

www.researchgate.net › ... › Robustness

Adversarial training (AT) aims to improve models' robustness against adversarial attacks by mixing clean data and adversarial examples (AEs) into training. Most ...

Blind Adversarial Training: Balance Accuracy and Robustness. - dblp

dblp.org › rec › corr › abs-2004-05914

Haidong Xie , Xueshuang Xiang, Naijin Liu, Bin Dong: Blind Adversarial Training: Balance Accuracy and Robustness. CoRR abs/2004.05914 (2020).

Blind Adversarial Pruning: Balance Accuracy, Efficiency and Robustness

ui.adsabs.harvard.edu › abs › arXiv:2004

This paper first investigates the robustness of pruned models with different compression ratios under the gradual pruning process and concludes that the ...

Blind Adversarial Pruning: Balance Accuracy, Efficiency and ... - Bytez

bytez.com › docs › arxiv › paper

This paper first investigates the robustness of pruned models with different compression ratios under the gradual pruning process and concludes that the ...

[PDF] Splitting the Difference on Adversarial Training 1 Introduction - USENIX

www.usenix.org › system › files

As a whole, our main contribution is a general method that confers a significant level of robustness upon classifiers with only minor or negligible degradation ...

Enhancing adversarial robustness for deep metric learning via neural ...

www.sciencedirect.com › article › abs › pii

May 13, 2024 · This paper proposes a novel framework for enhancing adversarial robustness and maintaining benign performance by introducing the concept of Neural Discrete ...

Towards Understanding Robustness Trade-off for Generalization

openreview.net › forum

Adversarial training is a commonly used technique to improve model robustness against adversarial examples. Despite its success as a defense mechanism, ...

Scholarly articles for Blind Adversarial Training: Balance Accuracy and Robustness.