DeepFake Detection
131 papers with code • 5 benchmarks • 18 datasets
DeepFake Detection is the task of detecting fake videos or images that have been generated using deep learning techniques. Deepfakes are created by using machine learning algorithms to manipulate or replace parts of an original video or image, such as the face of a person. The goal of deepfake detection is to identify such manipulations and distinguish them from real videos or images.
Description source: DeepFakes: a New Threat to Face Recognition? Assessment and Detection
Image source: DeepFakes: a New Threat to Face Recognition? Assessment and Detection
Benchmarks
These leaderboards are used to track progress in DeepFake Detection
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
|||||
|
|||||
|
|||||
|
|||||
|
Libraries
Use these libraries to find DeepFake Detection models and implementationsDatasets
FaceForensics++
Celeb-DF
DFDC
FaceForensics
WildDeepfake
FakeAVCeleb
DeeperForensics-1.0
KoDF
Most implemented papers
Rethinking the Up-Sampling Operations in CNN-based Generative Network for Generalizable Deepfake Detection
chuangchuangtan/npr-deepfakedetection
•
•
Recently, the proliferation of highly realistic synthetic images, facilitated through a variety of GANs and Diffusions, has significantly heightened the susceptibility to misuse.
Adversarial Deepfakes: Evaluating Vulnerability of Deepfake Detectors to Adversarial Examples
paarthneekhara/adversarialdeepfakes
•
•
Recent advances in video manipulation techniques have made the generation of fake videos more accessible than ever before.
Not made for each other- Audio-Visual Dissonance-based Deepfake Detection and Localization
MDS is computed as an aggregate of dissimilarity scores between audio and visual segments in a video.
FakePolisher: Making DeepFakes More Detection-Evasive by Shallow Reconstruction
At this moment, GAN-based image generation methods are still imperfect, whose upsampling design has limitations in leaving some certain artifact patterns in the synthesized image.
Deepfake Detection using Spatiotemporal Convolutional Networks
oidelima/Deepfake-Detection
•
•
Better generative models and larger datasets have led to more realistic fake videos that can fool the human eye but produce temporal and spatial artifacts that deep learning approaches can detect.
Artificial Fingerprinting for Generative Models: Rooting Deepfake Attribution in Training Data
ningyu1991/ArtificialGANFingerprints
•
•
ICCV 2021
Thus, we seek a proactive and sustainable solution on deepfake detection, that is agnostic to the evolution of generative models, by introducing artificial fingerprints into the models.
TweepFake: about Detecting Deepfake Tweets
To prevent this, it is crucial to develop deepfake social media messages detection systems.
A Convolutional LSTM based Residual Network for Deepfake Video Detection
Also, they do not take advantage of the temporal information of the video.
DeepFakesON-Phys: DeepFakes Detection based on Heart Rate Estimation
This work introduces a novel DeepFake detection framework based on physiological measurement.
Neural Deepfake Detection with Factual Structure of Text
jmpu/deepfaketextdetection
•
•
EMNLP 2020
To address this, we propose a graph-based model that utilizes the factual structure of a document for deepfake detection of text.
