English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

We show that label noise exists in adversarial training. Such label noise isdue to the mismatch between the true label distribution of adversarial examplesand the label inherited from clean examples - the true label distribution isdistorted by the adversarial perturbation, but is neglected by the commonpractice that inherits labels from clean examples. Recognizing label noisesheds insights on the prevalence of robust overfitting in adversarial training,and explains its intriguing dependence on perturbation radius and data quality.Also, our label noise perspective aligns well with our observations of theepoch-wise double descent in adversarial training. Guided by our analyses, weproposed a method to automatically calibrate the label to address the labelnoise and robust overfitting. Our method achieves consistent performanceimprovements across various models and datasets without introducing newhyper-parameters or additional tuning.

Label Noise in Adversarial Training: A Novel Perspective to Study Robust Overfitting