Evaluating the adversarial robustness of machine-learning models using gradient-based attacks is challenging. In this work, we show that hyperparameter optimization can improve fast minimum-norm attacks by automating the selection of the loss function, the optimizer, and the step-size scheduler, along with the corresponding hyperparameters. Our extensive evaluation involving several robust models demonstrates the improved efficacy of fast minimum-norm attacks when hyped up with hyperparameter optimization. We release our open-source code at https://github.com/pralab/HO-FMN.
Improving Fast Minimum-Norm Attacks with Hyperparameter Optimization
Giuseppe FlorisPrimo
;Raffaele Mura;Luca Scionis;Giorgio Piras
;Maura Pintor;Ambra DemontisPenultimo
;Battista BiggioUltimo
2023-01-01
Abstract
Evaluating the adversarial robustness of machine-learning models using gradient-based attacks is challenging. In this work, we show that hyperparameter optimization can improve fast minimum-norm attacks by automating the selection of the loss function, the optimizer, and the step-size scheduler, along with the corresponding hyperparameters. Our extensive evaluation involving several robust models demonstrates the improved efficacy of fast minimum-norm attacks when hyped up with hyperparameter optimization. We release our open-source code at https://github.com/pralab/HO-FMN.File in questo prodotto:
Non ci sono file associati a questo prodotto.
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.