UG100 Dataset

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, when and 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 available here.