Structure Estimation of Adversarial Distributions for Enhancing Model Robustness: A Clustering-Based Approach

Structure Estimation of Adversarial Distributions for Enhancing Model Robustness: A Clustering-Based Approach

In this paper, we propose an advanced method for adversarial training that focuses on leveraging the underlying structure of adversarial perturbation distributions. Unlike conventional adversarial training techniques that consider adversarial examples in isolation, our approach employs clustering al...

Full description

Bibliographic Details
Main Authors: Bader Rasheed, Adil Khan, Asad Masood Khattak
Format: Article
Language:English
Published: MDPI AG 2023-10-01
Series:Applied Sciences
Subjects:
deep neural networks
robustness
adversarial attacks
adversarial training
clustering
Online Access:https://www.mdpi.com/2076-3417/13/19/10972

Internet

https://www.mdpi.com/2076-3417/13/19/10972

Similar Items