A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf
.
Feature-Based Adversarial Training for Deep Learning Models Resistant to Transferable Adversarial Examples
2022
IEICE transactions on information and systems
Although deep neural networks (DNNs) have achieved high performance across a variety of applications, they can often be deceived by adversarial examples that are generated by adding small perturbations to the original images. Adversaries may generate adversarial examples using the property of transferability, in which adversarial examples that deceive one model can also deceive other models because adversaries do not obtain any information on the DNNs deployed in real scenarios. Recent studies
doi:10.1587/transinf.2021edp7198
fatcat:gu2mrqe54vb5nctck74ivaazpq