Adversarial training and attribution methods enable evaluation of robustness and interpretability of deep learning models for image classification

Flávio A.O. Santos, Cleber Zanchettin, Weihua Lei, Luís A. Nunes Amaral*

*Corresponding author for this work

Research output: Contribution to journal › Article › peer-review

Fingerprint

Dive into the research topics of 'Adversarial training and attribution methods enable evaluation of robustness and interpretability of deep learning models for image classification'. Together they form a unique fingerprint.

Keyphrases

Computer Science

Chemical Engineering

Earth and Planetary Sciences

Psychology