paper-with-me

홈 › Papers

Certified geometric robustness -- Super-DeepG

2026-04-27 · Noémie Cohen, Mélanie Ducoffe, Christophe Gabreau, Claire Pagetti, Xavier Pucel arxiv

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.

📄 PDF Abstract BibTeX arXiv:2604.24379

Code (0)

등록된 구현이 없습니다.

Tasks

Computational Efficiency

Similar Papers 제목 키워드 기반

A Geometric Graph-Based Deep Learning Model for Drug-Target Affinity Prediction

2025-09-15 · Md Masud Rana, Farjana Tasnim Mukta, Duc D. Nguyen arxiv

In structure-based drug design, accurately estimating the binding affinity between a candidate ligand and its protein receptor is a central challenge. Recent advances in artificial intelligence, particularly deep learnin…

Graph LearningDrug DiscoveryHoldout Set

Towards Universal Certified Robustness with Multi-Norm Training

2024-10-03 · Enyi Jiang, David S. Cheung, Gagandeep Singh

Existing certified training methods can only train models to be robust against a certain perturbation type (e.g. $l_\infty$ or $l_2$). However, an $l_\infty$ certifiably robust model may not be certifiably robust against…

Provable Defense Against Geometric Transformations

2022-07-22 · Rem Yang, Jacob Laurel, Sasa Misailovic, Gagandeep Singh

Geometric image transformations that arise in the real world, such as scaling and rotation, have been shown to easily deceive deep neural networks (DNNs). Hence, training DNNs to be certifiably robust to these perturbati…

Autonomous DrivingGPU

Certifying Geometric Robustness of Neural Networks

2019-12-01 · NeurIPS 2019 12 · Mislav Balunovic, Maximilian Baader, Gagandeep Singh, Timon Gehr 외

The use of neural networks in safety-critical computer vision systems calls for their robustness certification against natural geometric transformations (e.g., rotation, scaling). However, current certification methods t…

Deep Weakly Supervised Positioning

2021-04-10 · Ruoyu Wang, Xuchu Xu, Li Ding, Yang Huang 외

PoseNet can map a photo to the position where it is taken, which is appealing in robotics. However, training PoseNet requires full supervision, where ground truth positions are non-trivial to obtain. Can we train PoseNet…