30 datasets found

Deepfakes are synthetically generated images, videos or audios, which fraudsters use to manipulate legitimate information. The proposed technique outperforms state-of-the-art...

A comprehensive collection of contemporary codec models, resulting in the creation of the CodecFake dataset.

A dataset for deepfake detection challenge.

A novel multilingual and multimodal deepfake dataset.

A robustness and generalizability study of deepfake detection using diffusion models.

A challenging real-world dataset for deepfake detection.

A deepfake detection method that can address the issue of modifying segments of videos using generative techniques.

DeepfakeTIMIT dataset consists of 5,639 deepfake videos and 890 real videos.

Deepfake video detection using Generative Convolutional Vision Transformer (GenConViT) for deepfake video detection. Our model combines ConvNeXt and Swin Transformer models for...

The dataset used in the paper for testing the proposed Data-Independent Operator (DIO) framework for generalizable forgery image detection.

The DeepFake Detection Challenge (DFDC) dataset contains over 100,000 videos, including authentic and manipulated content.

The proposed GRACE method leverages feature entanglement with sparse constraints and a graph convolutional network with graph Laplacian smoothing prior regularization to...

Face forgery by deepfake is widely spread over the internet and has raised severe societal concerns. Recently, how to detect such forgery contents has become a hot research...

Face forgery by deepfake is widely spread over the internet and has raised severe societal concerns. Recently, how to detect such forgery contents has become a hot research...

A dedicated collection of images: real/pristine images collected from CelebA, FFHQ1, and ImageNet datasets and synthetic data generated by 9 different Generative Adversarial...

The Deep Fake Detection Competition (DFDC) dataset is a large-scale dataset for deepfake detection, containing 124,000 videos.

The dataset contains real and fake face videos.

The dataset contains real and fake face images generated by diffusion models.

The paper proposes a unified face forgery detection framework to solve the multi-dataset conflict problem, and the authors use five public autopilot datasets, including...

Diffusion noise feature: Accurate and fast generated image detection.