HacktivSpace/multidisciplinary-deepfake-detection
A solution for deepfake detection across multiple modalities, including images, audio, and video, using ML models like CNNs, Transformers, SVMs, Bayesian networks, and Vision Transformers. This repository includes data preprocessing, model training, evaluation scripts, and Docker support for deployment.
This solution helps analysts, journalists, and content moderators identify fabricated or manipulated content. It takes images, audio, or video files as input and uses various machine learning techniques to determine if the content is real or a deepfake. The output is a clear classification indicating whether the content is authentic or artificially generated, helping users distinguish genuine media from fakes.
No commits in the last 6 months.
Use this if you need to reliably detect deepfakes across different types of media like photos, spoken audio, and video clips.
Not ideal if you are looking for a simple, plug-and-play web tool and do not have technical expertise in running scripts or using Docker.
Stars
13
Forks
3
Language
Python
License
—
Category
Last pushed
Aug 18, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/HacktivSpace/multidisciplinary-deepfake-detection"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
DadaNanjesha/AI-Text-Humanizer-App
Transform AI-generated text into formal, human-like, and academic writing with ease, avoids AI detector!
Imalwayshere/Open-Detector
BERT-based AI-generated academic text detection model
davide-coccomini/MINTIME-Multi-Identity-size-iNvariant-TIMEsformer-for-Video-Deepfake-Detection
Code for Video Deepfake Detector from "MINTIME: Multi-Identity Size-Invariant Video Deepfake...
iamjr15/Ensemble-AI-Text-Detection
This project detects AI-generated text using an ensemble of classifiers: Multinomial Naive...
Polymath-Saksh/DeitFake
DeepFake Detection Model with a Self-Trained Data Efficient Image Transformers model.