Advanced AI model detects faces and identifies deep fake images.
Hive's Deepfake Image Detection model identifies whether or not an image is a deepfake.
The model locates faces in an image. For each detected face, this model outputs a bounding box for its location, a classification, and accompanying confidence score.
Image classification model that classifies whether an image is a deepfake.
This model is ready for commercial and non-commercial use.
This model is not owned or developed by NVIDIA. This model has been developed and built to a third-party’s requirements for this application and use case.
https://thehive.ai/terms-of-use
Architecture Type: Convolution Neural Network (CNN)]
Network Architecture: EfficientNet-B4, YoloV8
Input Type(s): Ensemble Gradient Boosted (EGB) Image
Input Format(s): PNG, JPEG, or JPG
Input Parameters: Two-Dimensional (2D)
Output Type(s): Image with bounding boxes, Text
Output Format: JPEG, String
Output Parameters: Two-Dimensional (2D) Image with the same shape as input, One Dimensional (1D)
Supported Hardware Microarchitecture Compatibility:
[Preferred/Supported] Operating System(s): Linux
v1.0
** Data Collection Method by dataset
** Labeling Method by dataset
Properties (Quantity, Dataset Descriptions, Sensor(s)): Trained on a large dataset comprising millions of artificially generated images and human-created images such as photographs, digital and traditional art, and memes sourced from across the web.
Engine: TensorRT
Test Hardware: L40
NVIDIA believes Trustworthy AI is a shared responsibility and we have established policies and practices to enable development for a wide array of AI applications. When downloaded or used in accordance with our terms of service, developers should work with their internal model team to ensure this model meets requirements for the relevant industry and use case and addresses unforeseen product misuse.
Please report security vulnerabilities or NVIDIA AI Concerns here.