Skip to content
SPECIFICTION
Get listed

DeepFake-O-Meter

zinc.cse.buffalo.edu

Web
Visit zinc.cse.buffalo.edu
Spec score 7.4 #13 of 20 in AI Deepfake Detection Tools

Spec sheet

Purpose
DeepFake-o-Meter aggregates results from research AI media detection models to support media authenticity assessment.Read 7 Oct 2026 · zinc.cse.buffalo.edu
Intended users
The University at Buffalo describes the platform as serving users including social media users, journalists, and law enforcement.Read 7 Oct 2026 · buffalo.edu
Headquarters
Buffalo, New York, United StatesRead 28 Sep 2026 · zinc.cse.buffalo.edu
Maker
The site attributes DeepFake-O-Meter to the University at Buffalo and the UB Media Forensics Lab.Read 7 Oct 2026 · zinc.cse.buffalo.edu
Account access
The site provides account sign-up and login pages, and its login page offers a guest option to return to the home page.Read 7 Oct 2026 · zinc.cse.buffalo.edu
Current use
The home page reports that Deepfake-o-Meter was used on the AFP fact check website to detect a deepfake video.Read 7 Oct 2026 · zinc.cse.buffalo.edu
Detection models
The models page lists 37 integrated forensic research models.Read 7 Oct 2026 · zinc.cse.buffalo.edu
Interpretation caveat
The platform provides analysis from multiple methods and does not make strong claims about whether uploaded content is authentic.Read 7 Oct 2026 · buffalo.edu
Media types
The platform analyzes images, videos, and audio.Read 7 Oct 2026 · buffalo.edu
Model categories
The model catalog includes methods labeled for image, video, and audio detection.Read 7 Oct 2026 · zinc.cse.buffalo.edu
Model limitations
The model catalog notes that WAV2LIP-STA performance may suffer under heavy compression.Read 7 Oct 2026 · zinc.cse.buffalo.edu
Model selection
Users can select detection algorithms using listed metrics that include accuracy, running time, and year developed.Read 7 Oct 2026 · buffalo.edu
Multiple analyses
The University at Buffalo says users can run multiple detection algorithms, each returning a percentage likelihood that content was AI generated.Read 7 Oct 2026 · buffalo.edu
Open source
The platform is described as open source, with algorithm source code publicly accessible.Read 7 Oct 2026 · buffalo.edu
Project team
The site identifies the UB Media Forensics Lab as the developer and lists Siwei Lyu as project director.Read 7 Oct 2026 · zinc.cse.buffalo.edu
Research models
The detection models page lists 37 integrated forensic research models.Read 7 Oct 2026 · zinc.cse.buffalo.edu
Result interpretation
The University at Buffalo says the platform provides analysis from a broad range of methods and leaves users to decide whether content is real.Read 7 Oct 2026 · buffalo.edu
Results
Each selected algorithm returns a percentage representing the likelihood that content was AI-generated.Read 7 Oct 2026 · buffalo.edu
Submission sharing
Before upload, users are asked whether they want to share the media with researchers; the team says shared submissions can help train detection algorithms.Read 7 Oct 2026 · buffalo.edu
Support contact
The contact page lists [email protected] for contacting the lab.Read 7 Oct 2026 · zinc.cse.buffalo.edu
User audience
The maker describes the platform as intended to make deepfake analysis available to the public, including social media users, journalists, and law enforcement.Read 7 Oct 2026 · buffalo.edu

Where Specifiction places it

Alternatives to DeepFake-O-MeterAll alternatives →