Shawn-Shan/fawkes

Health v2 · maintenance only

Adoption not part of the score

5595 stars · 510 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded

Fawkes is a privacy protection tool from University of Chicago researchers that adds imperceptible adversarial perturbations to photos to prevent unauthorized facial recognition models from identifying you. It is distributed as a Python CLI on PyPI with low/mid/high protection modes.

Use cases

• cloak my photos against facial recognition
• protect personal images from face recognition models
• add adversarial perturbations to photos before posting online
• prevent unauthorized face identification from scraped images
• research adversarial machine learning defenses against face recognition

When to choose

• you want to protect personal photos from being used to train or run facial recognition models
• you need a simple CLI to batch-process image directories with cloaking perturbations
• you are studying adversarial ML and privacy-enhancing technologies

When to avoid

• you need GPU acceleration out of the box - the packaged binary is CPU-only and GPU requires modifying the source
• you need real-time or fast processing - generation takes about 60 seconds per image on CPU
• you need a guarantee of protection - effectiveness against evolving models is not assured

Facets

cli-tool · maturity maintenance

image-processing machine-learning privacy cli privacy machine-learning image-processing security python cli cross-platform facial-recognition adversarial-examples cloaking face-recognition privacy-protection gpu

Member repositories

For agents

markdown · JSON · MCP: product_card(name="Shawn-Shan/fawkes")