Directional Adversarial Training for Cost Sensitive Deep Learning Classification Applications

10/08/2019
by   Matteo Terzi, et al.
5

In many real-world applications of Machine Learning it is of paramount importance not only to provide accurate predictions, but also to ensure certain levels of robustness. Adversarial Training is a training procedure aiming at providing models that are robust to worst-case perturbations around predefined points. Unfortunately, one of the main issues in adversarial training is that robustness w.r.t. gradient-based attackers is always achieved at the cost of prediction accuracy. In this paper, a new algorithm, called Wasserstein Projected Gradient Descent (WPGD), for adversarial training is proposed. WPGD provides a simple way to obtain cost-sensitive robustness, resulting in a finer control of the robustness-accuracy trade-off. Moreover, WPGD solves an optimal transport problem on the output space of the network and it can efficiently discover directions where robustness is required, allowing to control the directional trade-off between accuracy and robustness. The proposed WPGD is validated in this work on image recognition tasks with different benchmark datasets and architectures. Moreover, real world-like datasets are often unbalanced: this paper shows that when dealing with such type of datasets, the performance of adversarial training are mainly affected in term of standard accuracy.

READ FULL TEXT

page 4

page 6

page 14

11/19/2021

Fooling Adversarial Training with Inducing Noise

Adversarial training is widely believed to be a reliable approach to imp...
10/22/2018

Cost-Sensitive Robustness against Adversarial Examples

Several recent works have developed methods for training classifiers tha...
03/24/2021

Adversarial Feature Stacking for Accurate and Robust Predictions

Deep Neural Networks (DNNs) have achieved remarkable performance on a va...
10/22/2020

Once-for-All Adversarial Training: In-Situ Tradeoff between Robustness and Accuracy for Free

Adversarial training and its many variants substantially improve deep ne...
06/07/2019

Inductive Bias of Gradient Descent based Adversarial Training on Separable Data

Adversarial training is a principled approach for training robust neural...
10/13/2021

A Framework for Verification of Wasserstein Adversarial Robustness

Machine learning image classifiers are susceptible to adversarial and co...
03/30/2020

Towards Deep Learning Models Resistant to Large Perturbations

Adversarial robustness has proven to be a required property of machine l...