RobustNeuralNetworks.jl: a Package for Machine Learning and Data-Driven Control with Certified Robustness
Abstract
Neural networks are typically sensitive to small input perturbations, leading to unexpected or brittle behaviour. We present RobustNeuralNetworks.jl: a Julia package for neural network models that are constructed to naturally satisfy a set of user-defined robustness metrics. The package is based on the recently proposed Recurrent Equilibrium Network (REN) and Lipschitz-Bounded Deep Network (LBDN) model classes, and is designed to interface directly with Julia's most widely-used machine learning package, Flux.jl. We discuss the theory behind our model parameterization, give an overview of the package, and provide a tutorial demonstrating its use in image classification, reinforcement learning, and nonlinear state-observer design.
Cite
@article{arxiv.2306.12612,
title = {RobustNeuralNetworks.jl: a Package for Machine Learning and Data-Driven Control with Certified Robustness},
author = {Nicholas H. Barbara and Max Revay and Ruigang Wang and Jing Cheng and Ian R. Manchester},
journal= {arXiv preprint arXiv:2306.12612},
year = {2025}
}
Comments
Accepted to the Proceedings of the JuliaCon Conferences