Skip to content
#

adversarial-perturbations

Here are 13 public repositories matching this topic...

Protects personal and creator photos from AI scraping, training, and deepfake generation using adversarial perturbations. This tool implements targeted feature-shifting to mislead generative models while maintaining human visual quality. Features a modular architecture, GPU-accelerated optimization, and perceptual loss constraints (SSIM/LPIPS).

  • Updated Jan 8, 2026
  • Python

Improve this page

Add a description, image, and links to the adversarial-perturbations 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 adversarial-perturbations topic, visit your repo's landing page and select "manage topics."

Learn more