Robustifying Binary Classification to Adversarial Perturbation

10/29/2020
by   Fariborz Salehi, et al.
2

Despite the enormous success of machine learning models in various applications, most of these models lack resilience to (even small) perturbations in their input data. Hence, new methods to robustify machine learning models seem very essential. To this end, in this paper we consider the problem of binary classification with adversarial perturbations. Investigating the solution to a min-max optimization (which considers the worst-case loss in the presence of adversarial perturbations) we introduce a generalization to the max-margin classifier which takes into account the power of the adversary in manipulating the data. We refer to this classifier as the "Robust Max-margin" (RM) classifier. Under some mild assumptions on the loss function, we theoretically show that the gradient descent iterates (with sufficiently small step size) converge to the RM classifier in its direction. Therefore, the RM classifier can be studied to compute various performance measures (e.g. generalization error) of binary classification with adversarial perturbations.

READ FULL TEXT
POST COMMENT

Comments

There are no comments yet.

Authors

page 1

page 2

page 3

page 4

02/14/2017

On Detecting Adversarial Perturbations

Machine learning and deep learning in particular has advanced tremendous...
02/23/2018

Adversarial vulnerability for any classifier

Despite achieving impressive and often superhuman performance on multipl...
06/06/2020

Unique properties of adversarially trained linear classifiers on Gaussian data

Machine learning models are vulnerable to adversarial perturbations, tha...
04/06/2021

Taming Adversarial Robustness via Abstaining

In this work, we consider a binary classification problem and cast it in...
09/14/2016

Very Simple Classifier: a Concept Binary Classifier toInvestigate Features Based on Subsampling and Localility

We propose Very Simple Classifier (VSC) a novel method designed to incor...
07/10/2018

Fooling the classifier: Ligand antagonism and adversarial examples

Machine learning algorithms are sensitive to so-called adversarial pertu...
08/04/2020

Can Adversarial Weight Perturbations Inject Neural Backdoors?

Adversarial machine learning has exposed several security hazards of neu...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.