[ICCV 2023] Official implementation of the paper: "DIRE for Diffusion-Generated Image Detection"

Image Tampering Detection using ELA and CNN

Code and pre-trained models for our paper "CLIPping the Deception: Adapting Vision-Language Models for Universal Deepfake Detection".

VerifyVision-Pro是一个全面的图像伪造篡改检测解决方案，利用深度学习（deep learning）和计算机视觉技术（cv）精确识别各类图像篡改，包括deepfake、AI生成内容、拼接操作和复制-移动篡改。基于PyTorch实现，集成了从数据处理、模型训练到部署的完整工作流程。

Find helpful tools and resources to help you fact check and analyse, fake news and AI generated imagery.

Classifies a given image as authentic or tampered by doing two levels of analysis. Implemented using PyTorch.

Classifies a given aadhaar image to real or fake by doing two levels of analysis.

Dự án nghiên cứu khoa học sinh viên HVNH 2024 - 2025

패치 기반 딥페이크 영상 검출에 관한 연구

develop a Siamese Neural Network capable of performing binary classification based on the Euclidean distance between embedding vectors generated by the network. This classification helps in predicting whether an image is synthetic or real.

Zero-shot AI-generated image detection using forensic self-descriptions. Trained only on real images, detects deepfakes from any generator. Official implementation. CVPR 2025.

A project able to differentiate between REAL and FAKE images.

일반화 능력이 향상된 CNN 기반 위조 영상 식별

Fake Image Detection Using Machine Learning

색상 차이와 신경망을 이용한 위조 이미지 검출

YOLO-based image manipulation detection system

Separates real and fake images