Treatment of Statistical Estimation Problems in Randomized Smoothing for Adversarial Robustness
Fuente:
arXiv
Guardado en:
| Autor principal: | |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866917897532604416 |
|---|---|
| author | Voracek, Vaclav |
| author_facet | Voracek, Vaclav |
| contents | Randomized smoothing is a popular certified defense against adversarial attacks. In its essence, we need to solve a problem of statistical estimation which is usually very time-consuming since we need to perform numerous (usually $10^5$) forward passes of the classifier for every point to be certified. In this paper, we review the statistical estimation problems for randomized smoothing to find out if the computational burden is necessary. In particular, we consider the (standard) task of adversarial robustness where we need to decide if a point is robust at a certain radius or not using as few samples as possible while maintaining statistical guarantees. We present estimation procedures employing confidence sequences enjoying the same statistical guarantees as the standard methods, with the optimal sample complexities for the estimation task and empirically demonstrate their good performance. Additionally, we provide a randomized version of Clopper-Pearson confidence intervals resulting in strictly stronger certificates. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_17830 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Treatment of Statistical Estimation Problems in Randomized Smoothing for Adversarial Robustness Voracek, Vaclav Machine Learning Randomized smoothing is a popular certified defense against adversarial attacks. In its essence, we need to solve a problem of statistical estimation which is usually very time-consuming since we need to perform numerous (usually $10^5$) forward passes of the classifier for every point to be certified. In this paper, we review the statistical estimation problems for randomized smoothing to find out if the computational burden is necessary. In particular, we consider the (standard) task of adversarial robustness where we need to decide if a point is robust at a certain radius or not using as few samples as possible while maintaining statistical guarantees. We present estimation procedures employing confidence sequences enjoying the same statistical guarantees as the standard methods, with the optimal sample complexities for the estimation task and empirically demonstrate their good performance. Additionally, we provide a randomized version of Clopper-Pearson confidence intervals resulting in strictly stronger certificates. |
| title | Treatment of Statistical Estimation Problems in Randomized Smoothing for Adversarial Robustness |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2406.17830 |