Reachable sets of classifiers and regression models: (non-)robustness analysis and robust training

DOI10.1007/s10994-021-05973-0OpenAlexW3158840473MaRDI QIDQ2051310

Anna-Kathrin Kopetzki, Stephan Günnemann

Publication date: 24 November 2021

Published in: Machine Learning (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2007.14120

zbMATH Keywords

verificationrobustnessneural networkreachable set

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Related Items (1)

Automatic Abstraction Refinement in Neural Network Verification using Sensitivity Analysis

Uses Software

• UCI-ml
• PARVUS
• MNIST
• Reluplex
• Fashion-MNIST
• mixup
• AI2

Cites Work

• Determinants and the volumes of parallelotopes and zonotopes
• Hedonic housing prices and the demand for clean air
• Rigorously computed orbits of dynamical systems without the wrapping effect
• Reluplex: an efficient SMT solver for verifying deep neural networks
• Formal Verification of Piece-Wise Linear Feed-Forward Neural Networks

This page was built for publication: Reachable sets of classifiers and regression models: (non-)robustness analysis and robust training