.png){kind=icon}
.png){kind=icon}
Return
HO-FMN: Hyperparameter optimization for fast minimum-norm attacks
.png){kind=icon}
OA
AI
DOI：10.1016/j.neucom.2024.128918.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Gradient-based attacks area primary tool to evaluate robustness of machine-learning models. However, many attacks tend to provide overly-optimistic evaluations as they use fixed loss functions, optimizers, step-size schedulers, and default hyperparameters. In this work, we tackle these limitations by proposing a parametric variation of the well-known fast minimum-norm attack algorithm, whose loss, optimizer, step-size scheduler, and hyperparameters can be dynamically adjusted. We re-evaluate 12 robust models, showing that our attack finds smaller adversarial perturbations without requiring any additional tuning. This also enables reporting adversarial robustness as a function of the perturbation budget, providing amore complete evaluation than that offered by fixed-budget attacks, while remaining efficient. We release our open-source code at https: //github.com/pralab/HO-FMN.
Keywords:
Machine learning security
Adversarial examples
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.