Universal Adversarial Defense in Remote Sensing Based on Pre-trained Denoising Diffusion Models
Published in International Journal of Applied Earth Observation and Geoinformation, 2024
This paper is about the universal adversarial defense in remote sensing, which utilized a DDPM model to defend the deep learning models against the adversarial perturbations.
Recommended citation: Yu, W., Xu, Y. and Ghamisi, P. (2024) “Universal adversarial defense in remote sensing based on pre-trained denoising diffusion models,” International Journal of Applied Earth Observation and Geoinformation. Elsevier BV. Available at: https://doi.org/10.1016/j.jag.2024.104131.