Re-thinking model robustness from stability: a new insight to defend adversarial examples

DOI10.1007/S10994-022-06186-9MaRDI QIDQ2102317zbMATH OpenOpenAlexFDO

Authors Shufei Zhang, Kaizhu Huang, Zenglin Xu

Publication date 28 November 2022

Published in Machine Learning (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1911.06479

zbMATH Keywords

adversarial examplesadversarial generalizationadversarial trainingenergymodel robustness

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Cites work

• Analysis of classifiers' robustness to adversarial perturbations
• On the limited memory BFGS method for large scale optimization

Cited in

(1)

• Analysis of classifiers' robustness to adversarial perturbations

Describes a project that uses

Uses Software

• L-BFGS

This page was built for publication: Re-thinking model robustness from stability: a new insight to defend adversarial examples

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2102317)