Metrics and methods for robustness evaluation of neural networks with generative models

DOI10.1007/s10994-021-05994-9zbMath1525.68131arXiv2003.01993OpenAlexW3178258123MaRDI QIDQ6053812

Stavros Tripakis, Arseny Nerinovsky, Igor Buzhinsky

Publication date: 24 October 2023

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

Full work available at URL: https://arxiv.org/abs/2003.01993

zbMATH Keywords

generative modelsadversarial examplesnatural adversarial examplesreliable machine learning

Mathematics Subject Classification ID

Classification and discrimination; cluster analysis (statistical aspects) (62H30) Artificial neural networks and deep learning (68T07)

Cites Work

• Unnamed Item
• Analysis of classifiers' robustness to adversarial perturbations
• Safety verification of deep neural networks
• Reluplex: an efficient SMT solver for verifying deep neural networks
• An abstraction-based framework for neural network verification
• DeepSafe: a data-driven approach for assessing robustness of neural networks

This page was built for publication: Metrics and methods for robustness evaluation of neural networks with generative models