Skip to main content

Adversarial Attack for Uncertainty Estimation: Identifying Critical Regions in Neural Networks.

Alarab, I. and Prakoonwit, S., 2021. Adversarial Attack for Uncertainty Estimation: Identifying Critical Regions in Neural Networks. Neural Processing Letters. (In Press)

Full text available as:

[img]
Preview
PDF (OPEN ACCESS ARTICLE)
Alarab-Prakoonwit2021_Article_AdversarialAttackForUncertaint.pdf - Published Version
Available under License Creative Commons Attribution.

1MB

DOI: 10.1007/s11063-021-10707-3

Abstract

We propose a novel method to capture data points near decision boundary in neural network that are often referred to a specific type of uncertainty. In our approach, we sought to perform uncertainty estimation based on the idea of adversarial attack method. In this paper, uncertainty estimates are derived from the input perturbations, unlike previous studies that provide perturbations on the model’s parameters as in Bayesian approach. We are able to produce uncertainty with couple of perturbations on the inputs. Interestingly, we apply the proposed method to datasets derived from blockchain. We compare the performance of model uncertainty with the most recent uncertainty methods. We show that the proposed method has revealed a significant outperformance over other methods and provided less risk to capture model uncertainty in machine learning

Item Type:Article
ISSN:1370-4621
Uncontrolled Keywords:Uncertainty estimation ; Adversarial attack ; Neural Network ; Blockchain data
Group:Faculty of Science & Technology
ID Code:36455
Deposited By: Unnamed user with email symplectic@symplectic
Deposited On:05 Jan 2022 16:47
Last Modified:05 Jan 2022 16:47

Downloads

Downloads per month over past year

More statistics for this item...
Repository Staff Only -