Formal verification method using Lipschitz optimization on homographies to certify vision network robustness to camera pose changes in predominantly planar scenes.
Robustness of Rotation-Equivariant Networks to Adversarial Perturbations
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
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.
verdicts
UNVERDICTED 2representative citing papers
Invariance-inducing regularization using worst-case transformations reduces relative error by 20% on CIFAR10 transformed examples, improves standard accuracy on SVHN, outperforms equivariant networks, and proves no accuracy-robustness trade-off in the infinite data limit.
citing papers explorer
-
Lipschitz Optimization for Formal Verification of Homographies
Formal verification method using Lipschitz optimization on homographies to certify vision network robustness to camera pose changes in predominantly planar scenes.
-
Invariance-inducing regularization using worst-case transformations suffices to boost accuracy and spatial robustness
Invariance-inducing regularization using worst-case transformations reduces relative error by 20% on CIFAR10 transformed examples, improves standard accuracy on SVHN, outperforms equivariant networks, and proves no accuracy-robustness trade-off in the infinite data limit.