Adversarial Robustness via Adversarial Label-Smoothing

06/27/2019
by   Morgane Goibert, et al.
6

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 novel Label-Smoothing methods: adversarial, Boltzmann and second-best Label-Smoothing methods. On various datasets (MNIST, CIFAR10, SVHN) and models (linear models, MLPs, LeNet, ResNet), we show that these methods improve adversarial robustness against a variety of attacks (FGSM, BIM, DeepFool, Carlini-Wagner) by better taking account of the dataset geometry. These 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.

READ FULL TEXT

page 5

page 7

page 8

research
12/20/2022

In and Out-of-Domain Text Adversarial Robustness via Label Smoothing

Recently it has been shown that state-of-the-art NLP models are vulnerab...
research
09/17/2020

Label Smoothing and Adversarial Robustness

Recent studies indicate that current adversarial attack methods are flaw...
research
10/23/2020

An Investigation of how Label Smoothing Affects Generalization

It has been hypothesized that label smoothing can reduce overfitting and...
research
08/05/2017

Inception Score, Label Smoothing, Gradient Vanishing and -log(D(x)) Alternative

In this paper, we study several GAN related topics mathematically, inclu...
research
03/19/2020

RAB: Provable Robustness Against Backdoor Attacks

Recent studies have shown that deep neural networks (DNNs) are vulnerabl...
research
02/13/2021

Capturing Label Distribution: A Case Study in NLI

We study estimating inherent human disagreement (annotation label distri...
research
02/27/2020

Provable Robust Learning Based on Transformation-Specific Smoothing

As machine learning systems become pervasive, safeguarding their securit...

Please sign up or login with your details

Forgot password? Click here to reset