Search engine for discovering works of Art, research articles, and books related to Art and Culture
Javascript must be enabled to continue!
Out2In: Towards Machine Learning Models Resilient to Adversarial and Natural Distribution Shifts
View through CrossRef
Despite recent progress, the susceptibility of machine learning models
to adversarial examples remains a challenge —which calls for
rethinking the defense strategy. In this paper, we investigate the
cause-effect link between adversarial examples and the
out-of-distribution (OOD) problem. To that end, we propose Out2In, an
OOD generalization method that is resilient to not only adversarial but
also natural distribution shifts. Through an OOD to in-distribution
mapping intuition that leverages image-to-image translation, Out2In
translates OOD inputs to the data distribution used to train/test the
model. First, we experimentally confirm that the adversarial examples
problem is related to the wider OOD generalization problem. Then,
through extensive experiments on three benchmark image datasets (MNIST,
CIFAR10, and ImageNet), we show that Out2In consistently improves
robustness to OOD adversarial inputs and outperforms state-of-the-art
defenses by a significant margin, while preserving the exact accuracy on
benign (in-distribution) data. Furthermore, it generalizes on naturally
OOD inputs such as darker or sharper images
Title: Out2In: Towards Machine Learning Models Resilient to Adversarial and Natural Distribution Shifts
Description:
Despite recent progress, the susceptibility of machine learning models
to adversarial examples remains a challenge —which calls for
rethinking the defense strategy.
In this paper, we investigate the
cause-effect link between adversarial examples and the
out-of-distribution (OOD) problem.
To that end, we propose Out2In, an
OOD generalization method that is resilient to not only adversarial but
also natural distribution shifts.
Through an OOD to in-distribution
mapping intuition that leverages image-to-image translation, Out2In
translates OOD inputs to the data distribution used to train/test the
model.
First, we experimentally confirm that the adversarial examples
problem is related to the wider OOD generalization problem.
Then,
through extensive experiments on three benchmark image datasets (MNIST,
CIFAR10, and ImageNet), we show that Out2In consistently improves
robustness to OOD adversarial inputs and outperforms state-of-the-art
defenses by a significant margin, while preserving the exact accuracy on
benign (in-distribution) data.
Furthermore, it generalizes on naturally
OOD inputs such as darker or sharper images.
Related Results
Out2In: Towards Machine Learning Models Resilient to Adversarial and Natural Distribution Shifts
Out2In: Towards Machine Learning Models Resilient to Adversarial and Natural Distribution Shifts
<p> Despite recent progress, the susceptibility of machine learning models to adversarial examples remains a challenge —which calls for rethinking the defense strategy. In th...
Selection of Injectable Drug Product Composition using Machine Learning Models (Preprint)
Selection of Injectable Drug Product Composition using Machine Learning Models (Preprint)
BACKGROUND
As of July 2020, a Web of Science search of “machine learning (ML)” nested within the search of “pharmacokinetics or pharmacodynamics” yielded over 100...
ProDef-MDS: A Proactive Defense Mechanism Protecting Malware Detection Systems from Adversarial Attacks
ProDef-MDS: A Proactive Defense Mechanism Protecting Malware Detection Systems from Adversarial Attacks
Malware threatens cybersecurity by enabling data theft, unauthorized access, and extortion. Traditional malware detection systems (MDS) struggle with the increasing volume and comp...
Adversarial Machine Learning: Attack Vectors, Defences, and Robustness
Adversarial Machine Learning: Attack Vectors, Defences, and Robustness
<p><b><i><span>Background.</span></i></b><span> Adversarial machine learning has progressed from a marginal concern within machine l...
CREATING LEARNING MEDIA IN TEACHING ENGLISH AT SMP MUHAMMADIYAH 2 PAGELARAN ACADEMIC YEAR 2020/2021
CREATING LEARNING MEDIA IN TEACHING ENGLISH AT SMP MUHAMMADIYAH 2 PAGELARAN ACADEMIC YEAR 2020/2021
The pandemic Covid-19 currently demands teachers to be able to use technology in teaching and learning process. But in reality there are still many teachers who have not been able ...
Adversarial Training and Robustness in Machine Learning Frameworks
Adversarial Training and Robustness in Machine Learning Frameworks
In the realm of machine learning, ensuring robustness against adversarial attacks is increasingly crucial. Adversarial training has emerged as a prominent strategy to fortify model...
Adversarial-Aware Deep Learning System Based on a Secondary Classical Machine Learning Verification Approach
Adversarial-Aware Deep Learning System Based on a Secondary Classical Machine Learning Verification Approach
Deep learning models have been used in creating various effective image classification applications. However, they are vulnerable to adversarial attacks that seek to misguide the m...
Efficient Defense Against First Order Adversarial Attacks on Convolutional Neural Networks
Efficient Defense Against First Order Adversarial Attacks on Convolutional Neural Networks
Machine learning models, especially neural networks, are vulnerable to adversarial attacks, where inputs are purposefully altered to induce incorrect predictions. These adversarial...