Deepfake Detector
Deepfake Detector is a Python library designed for detecting deepfake content in images and videos. Leveraging advanced machine learning techniques, it provides an easy-to-use interface for real-time and batch processing of media files.
Features
- Real-time Deepfake Detection: Analyze live video feeds to detect deepfake content.
- Batch Processing: Process multiple images and videos to classify them as real or fake.
- Customizable Thresholds: Adjust detection sensitivity to suit your specific needs.
Installation
You can install the deepfake_detector package using pip:
pip install deepfake_detector
Usage
For Video Detection
Detect deepfake content in a video file. You can provide a video file path or use a webcam.
from deepfake_detector import live_video_prediction, image_prediction
# Set a custom threshold
live_video_prediction(source='name.mp4',threshold=0.5)
For Image Detection
Detect deepfake content in a single image.
from deepfake_detector import live_video_prediction, image_prediction
# Image prediction example
image_prediction('name.png', threshold=0.6)
Customizing Detection Threshold
You can set the threshold to control the sensitivity of the detection.
# Example with a higher sensitivity threshold
live_video_prediction(source='name.mp4',threshold=0.5)
image_prediction('name.png', threshold=0.6)
Paper Reference
For more detailed information about the techniques used in this library, please refer to the following research paper:
- Title: Deepfake Detection Using the Rate of Change between Frames Based on Computer Vision
- Journal: MDPI Sensors
- Abstract: This paper explores advanced methods for detecting deepfake media using convolutional neural networks (CNNs). The study provides a comprehensive analysis of various techniques and their effectiveness in identifying manipulated content.
Contributing
If you would like to contribute to the development of this library, please contact me.
Contact
For any questions or feedback, please contact:
- Author: Adupa Nithin Sai
- Email: adupanithinsai@gmail.com
- GitHub: https://github.com/saiadupa/Deepfake-detector
Thank you for using Deepfake Detector. We hope you find it useful for your deepfake detection needs!
Metadata
Release files for Deepfake-detector 1.4
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | |
|---|---|---|---|---|
| Deepfake-detector-1.4.tar.gz | 3.9 kB | Without provenance | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| Deepfake_detector-1.4-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 8.5 kB
Release files / Deepfake-detector-1.4.tar.gz
| Download URL | Deepfake-detector-1.4.tar.gz |
|---|---|
| Size | 3.9 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
6b086af59916ac3461e5c8113580e5faaf9d5e000602071161fa0ee5615cb0c0
|
|
BLAKE2b-256 checksum How to use checksums |
be7fcf265ecc15ba8c6e0205299b0d619b123845358acc002727f400de358e53
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/4.0.2 CPython/3.11.2
|
Release files / Deepfake_detector-1.4-py3-none-any.whl
| Download URL | Deepfake_detector-1.4-py3-none-any.whl |
|---|---|
| Size | 4.6 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
b2bcc75533cffde4b2fe500edabafec555f0a5adfe6b8f6ef657cef35769c7f1
|
|
BLAKE2b-256 checksum How to use checksums |
6ec586d74366b21d5a97db3b8253d458b69cb4ef5eb6c70fb2fbd55931f65863
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/4.0.2 CPython/3.11.2
|
Security for Deepfake-detector 1.4
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.