Adversarial Attack for Uncertainty Estimation: Identifying Critical Regions in Neural Networks
This provides a novel uncertainty estimation approach for machine learning practitioners, particularly in blockchain-related applications.
The paper tackles uncertainty estimation in neural networks by using adversarial attacks on inputs rather than model parameters, achieving significant outperformance over recent methods with reduced risk.
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.