# Robustness of Rotation-Equivariant Networks to Adversarial Perturbations Source: [Robustness of Rotation-Equivariant Networks to Adversarial Perturbations]() Collection index: [llms.txt]() Data updated: 2025-10-25T21:03:11.991Z Authors: Beranger Dumont, Simona Maggio, Pablo Montalvo Published: 2018-02-19T13:49:15.000Z ## Abstract Deep neural networks have been shown to be vulnerable to adversarial examples: very small perturbations of the input having a dramatic impact on the predictions. A wealth of adversarial attacks and distance metrics to quantify the similarity between natural and adversarial images have been proposed, recently enlarging the scope of adversarial examples with geometric transformations beyond pixel-wise attacks. In this context, we investigate the robustness to adversarial attacks of new Convolutional Neural Network architectures providing equivariance to rotations. We found that rotation-equivariant networks are significantly less vulnerable to geometric-based attacks than regular networks on the MNIST, CIFAR-10, and ImageNet datasets. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. ## Original sources and implementation [Original paper]() [PDF]()