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.

arXiv comment15 pages, 6 figures, Neural Process Lett (2021)

References in corpus (16)

• PyTorch: An Imperative Style, High-Performance Deep Learning Library
• Explaining and Harnessing Adversarial Examples
• Intriguing properties of neural networks
• A Review of Uncertainty Quantification in Deep Learning: Techniques, Applications and Challenges
• Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning
• Evasion Attacks against Machine Learning at Test Time
• GPyTorch: Blackbox Matrix-Matrix Gaussian Process Inference with GPU Acceleration
• Adversarial Attacks and Defences: A Survey
• Uncertainty Estimation Using a Single Deep Deterministic Neural Network
• Understanding Measures of Uncertainty for Adversarial Example Detection
• Adversarial Examples, Uncertainty, and Transfer Testing Robustness in Gaussian Process Hybrid Deep Networks
• Anti-Money Laundering in Bitcoin: Experimenting with Graph Convolutional Networks for Financial Forensics
• Implicit Weight Uncertainty in Neural 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