UG100 Dataset
DOI10.5281/zenodo.6869110Zenodo6869110MaRDI QIDQ6701812FDOQ6701812
Dataset published at Zenodo repository.
Samuele Marro, Michele Lombardi
Publication date: 19 July 2022
Copyright license: MIT license
The UG100 dataset contains the adversarial attack results of seven\(L_\infty\) approximate attacks (+ MIP) on the MNIST and CIFAR10 datasets. Specifically, it contains ~2.3k adversarial examples generated by the following attacks: Basic Iterative Method (bim) Brendel Bethge Attack (brendel) Carlini Wagner Attack (carlini) Deepfool (deepfool) Fast Gradient Sign Method (fast_gradient) Projected Gradient Descent (pgd) Uniform noise (uniform) MIPVerify (mip) It also includes adversarial distances (for all attacks) and bounds (for MIP), as well as MIP convergence times. Applications of this dataset include: Studying how, whenand why adversarial attacks are close-to-optimal; Training classifiers that are robust to adversarial noise; Benchmarking new adversarial attacks. The companion code for this dataset is availablehere.
This page was built for dataset: UG100 Dataset
