Reproduce “DeepFake-O-Meter v2.0: An Open Platform for DeepFake Detection” on OpenResearch

Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.

Universal app for Apple silicon and Intel. Requires macOS 11 or later.

About this paper

Yan Ju, Chengzhe Sun, Shan Jia, Shuwei Hou, Zhaofeng Si, Soumyya Kanti Datta, Lipeng Ke, Riky Zhou and 2 more

DeepFake-O-Meter v2.0 provides a platform to access and compare open-source detectors for images, video, and audio. Users submit media, select methods, and view outputs on the same input. Over four months, 445 users submitted 4,091 tasks. Average detector running times were about 30 seconds for image and audio and 90 seconds for video; the paper does not evaluate real-world accuracy.

Summary by alphaXiv.

Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.