Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Certified geometric robustness -- Super-DeepG

About

Safety-critical applications are required to perform as expected in normal operations. Image processing functions are often required to be insensitive to small geometric perturbations such as rotation, scaling, shearing or translation. This paper addresses the formal verification of neural networks against geometric perturbations on their image dataset. Our method Super-DeepG improves the reasoning used in linear relaxation techniques and Lipschitz optimization, and provides an implementation that leverages GPU hardware. By doing so, Super-DeepG achieves both precision and computational efficiency of robustness certification, to an extent that outperforms prior work. Super-DeepG is shared as an open-source tool on GitHub.

No\'emie Cohen, M\'elanie Ducoffe, Christophe Gabreau, Claire Pagetti, Xavier Pucel• 2026

Related benchmarks

TaskDatasetResultRank
Robustness VerificationMNIST first 100 images (test)
Certified Rate100
13
Geometric Robustness CertificationTinyImageNet VNN-Comp'24 model
Certified Accuracy (%)18
10
Robustness VerificationCIFAR10 first 100 images (test)
Certified Accuracy75
9
Certified Robustness (Scaling 1)CIFAR10
Certified Accuracy75
6
Certified Robustness (Shearing 2)CIFAR10
Certified Accuracy69
6
Certified Robustness (Shearing 2)TinyImageNet VNNComp'24
Certified Accuracy (%)48
6
Certified Robustness (Rotation 10)CIFAR10
Certified Accuracy (%) (Rotation 10)65
5
Certified Robustness (Rotation 30)MNIST
Certified Accuracy (Rotation 30)98
5
Certified Robustness (Scaling 2)TinyImageNet VNNComp'24
Certified Accuracy (%)36
5
Geometric CertificationMNIST R(30°)
Certified Accuracy94.3
2
Showing 10 of 14 rows

Other info

Follow for update