Image Forgery Detection and Localization (and related) Papers List

AutoSplice: A Text-prompt Manipulated Image Dataset for Media Forensics, WMF@CVPR2023

This GitHub provides different DeepFakes Detectors using facial regions and considering three different state-of-the-art fake detection systems.

This repository contains the official implementation (PyTorch) of "Multimodal Forgery Detection Using Ensemble Learning" proposed in APSIPA Paper 2022.

Agent skill for deepfake detection & media safety — detect AI-generated audio, images, and video with Resemble AI

Deep learning system achieving 95.36% accuracy in media forgery detection using hybrid ResNet50+ViT architecture. Optimized for 20% training data efficiency with PyTorch, OpenCV, and Flask-based inference pipeline. Live demo on Hugging Face Spaces.

🎭🔍 Detecting deepfake videos and images using Deep Learning with a Tkinter desktop interface

Production-ready Multimodal Lip Sync Detection & Deepfake Detection System. Detects audio-video synchronization mismatches using deep learning (PyTorch) with a scalable FastAPI-based inference pipeline. Optimized for real-time processing,low false positives, and robust performance on noisy speech segments. Built for video forensics,synthetic media

An Agentic AI system for Deepfake Detection & Media Authenticity Verification. Features autonomous model routing, an ensemble of 6 specialized neural networks, and advanced bias correction mechanisms.

A deep learning-based web application for deepfake video detection, powered by the fine-tuned XceptionNet (Extreme Inception) model. The system allows users to upload videos for deepfake detection, processes them through the trained model, and provides results via a clean Django-based web interface.

Beta tool for embedding and verifying digital authenticity in images, audio, and video using watermarks, C2PA, and steganography.

A modular PyTorch-based research lab for deepfake detection. Includes implementations and experiments with autoencoders, classifiers, contrastive learning, and generative-model–based detection techniques. Designed for benchmarking, reproducibility, and rapid exploration of new architectures.

This project implements the algorithm proposed in the paper: "A Novel Hybrid DCT and DWT Based Robust Watermarking Algorithm for Color Images" by Ahmed Khaleel Abdulrahman and Serkan Ozturk.

Full-stack AI media analysis platform with authentication, upload workflows, forensic scoring, and responsible transformation tools.

Physics-Anchored Deepfake Detection Framework

InSwapper Detector is a production-focused deepfake detection system designed to identify faces manipulated with INSwapper. It combines face detection, RGB image analysis, frequency artifact extraction, and a multi-task ConvNeXt-Tiny model for image, batch, and video-based detection.

Deepfake video detection using a deep CNN (4 conv blocks with BatchNorm + Dropout). Extracts frames from real/fake videos in the DFFMD dataset and classifies them through multi-frame analysis. TensorFlow/Keras.