Face Privacy
Fawkes
Introduced by Shan et al. in Fawkes: Protecting Privacy against Unauthorized Deep Learning ModelsFawkes is an image cloaking system that helps individuals inoculate their images against unauthorized facial recognition models. Fawkes achieves this by helping users add imperceptible pixel-level changes ("cloaks") to their own photos before releasing them. When used to train facial recognition models, these "cloaked" images produce functional models that consistently cause normal images of the user to be misidentified.
Source: Fawkes: Protecting Privacy against Unauthorized Deep Learning Models
Papers
| Paper | Code | Results | Date | Stars |
|---|
Tasks
| Task | Papers | Share |
|---|---|---|
| Data Poisoning | 4 | 44.44% |
| Face Recognition | 2 | 22.22% |
| Privacy Preserving Deep Learning | 2 | 22.22% |
| Image Generation | 1 | 11.11% |
Usage Over Time
Components
| Component | Type |
|
|---|---|---|
| 🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |
