Active machine learning approach to adversarial training improves trade-off between natural accuracy and adversarial robustness.

Mirsadeghi SMH.

Open source

DOI
10.1038/s41598-026-50378-5
Published
2026-04-28
Container
Sci Rep
Publisher
Not recorded
Open access
yes

Credibility signals

uncertain Score 53/100 under policy 1.0.0. This is a metadata assessment, not a judgment of the paper's conclusions.

Show all credibility signals

Cite this work

BibTeX

@article{allodium:10.1038/s41598-026-50378-5,
  title = {Active machine learning approach to adversarial training improves trade-off between natural accuracy and adversarial robustness.},
  author = {Mirsadeghi SMH.},
  year = {2026},
  journal = {Sci Rep},
  doi = {10.1038/s41598-026-50378-5},
  url = {https://doi.org/10.1038/s41598-026-50378-5}
}

RIS

TY  - JOUR
TI  - Active machine learning approach to adversarial training improves trade-off between natural accuracy and adversarial robustness.
AU  - Mirsadeghi SMH.
PY  - 2026
JO  - Sci Rep
DO  - 10.1038/s41598-026-50378-5
UR  - https://doi.org/10.1038/s41598-026-50378-5
ER  -

APA

SMH., M. (2026). Active machine learning approach to adversarial training improves trade-off between natural accuracy and adversarial robustness.. Sci Rep. https://doi.org/10.1038/s41598-026-50378-5

Source records