paper-with-me

홈 › Papers

Certifying Geometric Robustness of Neural Networks

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

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 target mostly norm-based pixel perturbations and cannot certify robustness against geometric transformations. In this work, we propose a new method to compute sound and asymptotically optimal linear relaxations for any composition of transformations. Our method is based on a novel combination of sampling and optimization. We implemented the method in a system called DeepG and demonstrated that it certifies significantly more complex geometric transformations than existing methods on both defended and undefended networks while scaling to large architectures.

📄 PDF Abstract BibTeX

Code (1)

eth-sri/deepg 공식 구현 tf

Similar Papers 제목 키워드 기반

Certifying Robustness via Topological Representations

2025-01-18 · Jens Agerberg, Andrea Guidolin, Andrea Martinelli, Pepijn Roos Hoefgeest 외

We propose a neural network architecture that can learn discriminative geometric representations of data from persistence diagrams, common descriptors of Topological Data Analysis. The learned representations enjoy Lipsc…

Topological Data Analysis

Semantic Robustness Certification for Vision-Language Models

2026-06-17 · Peiyu Yang, Paul Montague, Feng Liu, Andrew C. Cullen 외 arxiv

Vision-language models (VLMs) are now widely used in downstream tasks. However, real-world applications often expose VLMs to distribution shifts induced by semantic variation (e.g., shape, size, and style). Robustness ce…

Incremental Randomized Smoothing Certification

2023-05-31 · Shubham Ugare, Tarun Suresh, Debangshu Banerjee, Gagandeep Singh 외

Randomized smoothing-based certification is an effective approach for obtaining robustness certificates of deep neural networks (DNNs) against adversarial attacks. This method constructs a smoothed DNN model and certifie…

Robust Certification for Laplace Learning on Geometric Graphs

2021-04-22 · Matthew Thorpe, Bao Wang

Graph Laplacian (GL)-based semi-supervised learning is one of the most used approaches for classifying nodes in a graph. Understanding and certifying the adversarial robustness of machine learning (ML) algorithms has att…

Adversarial AttackAdversarial Robustness

Robust Validation to Geometric Perturbations for Autonomous Pose Estimation

2026-08-21 · Gregoire Theau, Melanie Ducoffe arxiv

Deploying autonomous systems in safety-critical domains demands guaranteed robustness against physically plausible geometric perturbations rather than abstract pixel-wise noise. In vision-based navigation and autonomous …

Object DetectionPose Estimation