English

Improving Hyperspectral Adversarial Robustness Under Multiple Attacks

Machine Learning 2023-05-12 v4 Cryptography and Security Computer Vision and Pattern Recognition

Abstract

Semantic segmentation models classifying hyperspectral images (HSI) are vulnerable to adversarial examples. Traditional approaches to adversarial robustness focus on training or retraining a single network on attacked data, however, in the presence of multiple attacks these approaches decrease in performance compared to networks trained individually on each attack. To combat this issue we propose an Adversarial Discriminator Ensemble Network (ADE-Net) which focuses on attack type detection and adversarial robustness under a unified model to preserve per data-type weight optimally while robustifiying the overall network. In the proposed method, a discriminator network is used to separate data by attack type into their specific attack-expert ensemble network.

Keywords

Cite

@article{arxiv.2210.16346,
  title  = {Improving Hyperspectral Adversarial Robustness Under Multiple Attacks},
  author = {Nicholas Soucy and Salimeh Yasaei Sekeh},
  journal= {arXiv preprint arXiv:2210.16346},
  year   = {2023}
}

Comments

6 pages, 2 figures, 1 table, 1 algorithm

R2 v1 2026-06-28T04:44:33.178Z