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

DOI10.1007/s10994-022-06186-9OpenAlexW4282918038MaRDI QIDQ2102317

Kaizhu Huang, Zenglin Xu, Shufei Zhang

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

energymodel robustnessadversarial examplesadversarial trainingadversarial generalization

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Uses Software

• L-BFGS

Cites Work

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

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