davide-coccomini/Adversarial-Magnification-to-Deceive-Deepfake-Detection-through-Super-Resolution

Official code for the paper "Adversarial Magnification to Deceive Deepfake Detection through Super Resolution"

24
/ 100
Experimental

This project helps anyone working with visual media to subtly alter images so that automated deepfake detection systems are less likely to identify them as fake. It takes an image (either genuine or already faked) and applies a super-resolution technique, which introduces minimal visual changes but significantly impairs deepfake detectors. Anyone who needs to make deepfakes harder to detect, or wants to create false positives in detection systems, would use this tool.

No commits in the last 6 months.

Use this if you need to make deepfake content more difficult for AI detection systems to identify, or if you want to test the robustness of deepfake detectors by generating false alarms.

Not ideal if you are looking to create deepfake content from scratch or to improve the visual quality of images for general purposes.

deepfake-creation media-manipulation digital-forensics visual-content-security adversarial-testing
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 5 / 25
Maturity 8 / 25
Community 11 / 25

How are scores calculated?

Stars

12

Forks

2

Language

Python

License

Last pushed

Jun 26, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/davide-coccomini/Adversarial-Magnification-to-Deceive-Deepfake-Detection-through-Super-Resolution"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.