This repo contains the ENF-WHU audio recording dataset collected around Wuhan University campus and the MATLAB programs for electronic network frequency (ENF) detection, enhancement, and robust estimation, in ENF-based audio forensic applications.
Includes three methods for median filtering forensics in digital images
MATLAB code for the Robust LAD-LRT ENF Detection (ICASSP 2023)
Official code for CapST (ACM TOMM 2025): A Capsule Network and Temporal Attention-based framework for Deepfake Model Attribution. Achieves efficient and accurate source identification across DFDM and GAN-generated datasets.
Official code for FAME: A lightweight spatio-temporal framework for Deepfake Model Attribution using VGG-based feature extraction and temporal attention. Outperforms prior methods across DFDM, FF++, and FakeAVCeleb datasets.
Structure matters: analyzing videos via graph neural networks for social media platform attribution
Contribution: This repository extends the original CLIP implementation by adding training code for an SVM classifier using CLIP-extracted features, with detailed setup instructions in README_TRAIN.md.
Add a description, image, and links to the multimedia-forensics topic page so that developers can more easily learn about it.
To associate your repository with the multimedia-forensics topic, visit your repo's landing page and select "manage topics."