Log In Sign Up

Training Strategies and Data Augmentations in CNN-based DeepFake Video Detection

by   Luca Bondi, et al.

The fast and continuous growth in number and quality of deepfake videos calls for the development of reliable detection systems capable of automatically warning users on social media and on the Internet about the potential untruthfulness of such contents. While algorithms, software, and smartphone apps are getting better every day in generating manipulated videos and swapping faces, the accuracy of automated systems for face forgery detection in videos is still quite limited and generally biased toward the dataset used to design and train a specific detection system. In this paper we analyze how different training strategies and data augmentation techniques affect CNN-based deepfake detectors when training and testing on the same dataset or across different datasets.


page 3

page 5


Improving DeepFake Detection Using Dynamic Face Augmentation

The creation of altered and manipulated faces has become more common due...

Spatiotemporal CNNs for Pornography Detection in Videos

With the increasing use of social networks and mobile devices, the numbe...

WildDeepfake: A Challenging Real-World Dataset for Deepfake Detection

In recent years, the abuse of a face swap technique called deepfake Deep...

The Do's and Don'ts for CNN-based Face Verification

While the research community appears to have developed a consensus on th...

Data Augmentation for Hypernymy Detection

The automatic detection of hypernymy relationships represents a challeng...

Metamorphic Testing-based Adversarial Attack to Fool Deepfake Detectors

Deepfakes utilise Artificial Intelligence (AI) techniques to create synt...

Finding Facial Forgery Artifacts with Parts-Based Detectors

Manipulated videos, especially those where the identity of an individual...