Improving Fast Minimum-Norm Attacks with Hyperparameter Optimization

Giuseppe Floris

First

;Raffaele Mura;Luca Scionis;Giorgio Piras

;Maura Pintor;Ambra Demontis

Penultimate

;Battista Biggio

Last

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.