Skip to content
#

perturbation-analysis

Here are 21 public repositories matching this topic...

Traffic light and sign recognition are key for Autonomous Vehicles (AVs) because perception mistakes directly influence navigation and safety. In addition to digital adversarial attacks, models are vulnerable to existing perturbations (glare, rain, dirt, or graffiti), which could lead to dangerous misclassifications.

  • Updated Jan 6, 2026
  • Python

Reproducible GHSA study of Fludd's 1617 Utriusque Cosmi Historia: a typed relational graph encodes the monochord's proportional grammar; six invariants are subjected to a seeded N=100 perturbation regime and a stability surface is measured. E0–E3 evidence never collapsed; the experiment is the authority.

  • Updated Aug 29, 2026
  • Python

Add this topic to your repo

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

Learn more