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

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.

15 pages, 6 figures, Neural Process Lett (2021)

References in corpus (8)

• PyTorch: An Imperative Style, High-Performance Deep Learning Library
• Explaining and Harnessing Adversarial Examples
• A Review of Uncertainty Quantification in Deep Learning: Techniques, Applications and Challenges
• Evasion Attacks against Machine Learning at Test Time
• Adversarial Examples, Uncertainty, and Transfer Testing Robustness in Gaussian Process Hybrid Deep Networks
• On Feature Collapse and Deep Kernel Learning for Single Forward Pass Uncertainty
• Understanding the Interaction of Adversarial Training with Noisy Labels
• DropConnect Is Effective in Modeling Uncertainty of Bayesian Deep Networks