Skip to content
#

adversarially-robust

Star

Here is 1 public repository matching this topic...

techySPHINX / ResUpNet

Star 0

ResUpNet is a deep learning–based defense framework designed to protect image classification models from adversarial attacks. It operates by transforming images into the YCbCr color space and selectively removing perturbations from the luminance (Y) channel using a ResNet-based upsampling architecture, while preserving color information.

high-fidelity neural-architecture adversarially-robust signal-refinement transformation-based
  • Updated Jun 23, 2026
  • Jupyter Notebook

Improve this page

Add a description, image, and links to the adversarially-robust topic page so that developers can more easily learn about it.

Curate this topic

Add this topic to your repo

To associate your repository with the adversarially-robust topic, visit your repo's landing page and select "manage topics."

Learn more