# Adversarial Robustness via Label-Smoothing

arXiv: https://arxiv.org/abs/1906.11567 · HTML: https://mlsanity.com/paper/1906.11567/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Jun 2019.

## Built on by (most cited first, 5 of 5)

- [Adaptive Label Smoothing To Regularize Large-Scale Graph Training](https://mlsanity.com/paper/2108.13555/) (2021)
- [In and Out-of-Domain Text Adversarial Robustness via Label Smoothing](https://mlsanity.com/paper/2212.10258/) (2022)
- [ROPUST: Improving Robustness through Fine-tuning with Photonic Processors and Synthetic Gradients](https://mlsanity.com/paper/2108.04217/) (2021)
- [Label Smoothing is Robustification against Model Misspecification](https://mlsanity.com/paper/2305.08501/) (2023)
- [Identifying and Exploiting Structures for Reliable Deep Learning](https://mlsanity.com/paper/2108.07083/) (2021)

## Abstract (arXiv)

We study Label-Smoothing as a means for improving adversarial robustness of supervised deep-learning models. After establishing a thorough and unified framework, we propose several variations to this general method: adversarial, Boltzmann and second-best Label-Smoothing methods, and we explain how to construct your own one. On various datasets (MNIST, CIFAR10, SVHN) and models (linear models, MLPs, LeNet, ResNet), we show that Label-Smoothing in general improves adversarial robustness against a variety of attacks (FGSM, BIM, DeepFool, Carlini-Wagner) by better taking account of the dataset geometry. The proposed Label-Smoothing methods have two main advantages: they can be implemented as a modified cross-entropy loss, thus do not require any modifications of the network architecture nor do they lead to increased training times, and they improve both standard and adversarial accuracy.