# Deepfake Detection

A vision-language encoder model fine-tuned based on SigLIP2 for detecting whether images are fake or real

A Vision Transformer-based binary classification model specifically designed for detecting deepfake images, with an accuracy rate of 99.2%

This is a Vision Transformer model for detecting AI-generated images in forensic applications, trained on the largest dataset to date.

A binary classification model using fine-tuned Vision Transformer (ViT) to detect deepfake images

A fine-tuned version based on MCG-NJU/videomae-large model on the deepfake detection challenge dataset, used for video deepfake detection.

FLODA is an advanced deepfake detection model that integrates image caption generation and authenticity assessment functions, achieving high-precision detection through visual question answering tasks.

A Vision Transformer model for detecting deepfake images, achieving high-precision forgery detection through contrastive learning and global-local similarity analysis.

A deepfake image detection model fine-tuned based on the SigLIP2 vision-language encoder for binary classification of real vs. synthetic images

An image classification model based on Vision Transformer architecture, specifically designed to detect AI-generated fake images

An image classification model based on Vision Transformer architecture, used to detect real images versus AI-generated fake images.

AI-generated image detection model developed by Sumsub, specifically designed to identify synthetic images created by tools like Stable Diffusion