Adversarial Robustness via Label-Smoothing - Archive ouverte HAL Access content directly
Preprints, Working Papers, ... Year :

Adversarial Robustness via Label-Smoothing

Robustesse Adversaire via Label-Smoothing

Morgane Goibert
  • Function : Author
  • PersonId : 1062855
Elvis Dohmatob
  • Function : Author
  • PersonId : 956319


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.
Fichier principal
Vignette du fichier
Article_adversarial_label_smoothing.pdf (3.59 Mo) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-02437752 , version 1 (13-01-2020)


  • HAL Id : hal-02437752 , version 1


Morgane Goibert, Elvis Dohmatob. Adversarial Robustness via Label-Smoothing. 2020. ⟨hal-02437752⟩
170 View
188 Download


Gmail Facebook Twitter LinkedIn More