# Achieving Generalizable Robustness of Deep Neural Networks by Stability Training

Source: [Achieving Generalizable Robustness of Deep Neural Networks by Stability Training](<https://www.sota2.com/research/paper/68fa66ae1e209131cea11b73>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T21:56:21.324Z

Authors: Jan Laermann, Wojciech Samek, Nils Strodthoff

Published: 2019-06-03T12:20:43.000Z

## Abstract

We study the recently introduced stability training as a general-purpose method to increase the robustness of deep neural networks against input perturbations. In particular, we explore its use as an alternative to data augmentation and validate its performance against a number of distortion types and transformations including adversarial examples. In our image classification experiments using ImageNet data stability training performs on a par or even outperforms data augmentation for specific transformations, while consistently offering improved robustness against a broader range of distortion strengths and types unseen during training, a considerably smaller hyperparameter dependence and less potentially negative side effects compared to data augmentation.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/1906.00735>)

[PDF](<https://arxiv.org/pdf/1906.00735.pdf>)