Improving Hyperspectral Adversarial Robustness Under Multiple Attacks
This work addresses a specific vulnerability in hyperspectral image analysis for applications like remote sensing, but it is incremental as it builds on existing adversarial robustness methods by extending them to handle multiple attack types.
The paper tackles the problem of adversarial robustness in hyperspectral image semantic segmentation under multiple attacks, proposing an Adversarial Discriminator Ensemble Network (ADE-Net) that uses a discriminator to detect attack types and route data to specialized expert networks, resulting in improved performance compared to traditional single-network approaches.
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.