MesoNet: a Compact Facial Video Forgery Detection Network

@article{Afchar2018MesoNetAC,
  title={MesoNet: a Compact Facial Video Forgery Detection Network},
  author={Darius Afchar and Vincent Nozick and Junichi Yamagishi and Isao Echizen},
  journal={2018 IEEE International Workshop on Information Forensics and Security (WIFS)},
  year={2018},
  pages={1-7}
}
This paper presents a method to automatically and efficiently detect face tampering in videos, and particularly focuses on two recent techniques used to generate hyper-realistic forged videos: Deepfake and Face2Face. [...] Key Result The tests demonstrate a very successful detection rate with more than 98% for Deepfake and 95% for Face2Face.Expand
A Detect method for deepfake video based on full face recognition
  • Kai Feng, Jan Wu, Min Tian
  • 2020 IEEE International Conference on Information Technology,Big Data and Artificial Intelligence (ICIBA)
  • 2020
In recent years, with the continuous upgrading of computer hardware and the continuous development of deep learning technology, new multimedia tampering tools can make it easier for people to tamperExpand
Exposing DeepFake Videos Using Attention Based Convolutional LSTM Network
  • Yishan Su, Huawei Xia, Qi Liang, Weizhi Nie
  • Computer Science
  • Neural Process. Lett.
  • 2021
TLDR
A novel attention-based deep fake video detection method, which captures the sharp changes in terms of the facial features caused by the composite video, and utilizes the convolutional long short-term memory to extract both spatial and temporal information of DeeFake videos. Expand
Capsule-forensics: Using Capsule Networks to Detect Forged Images and Videos
  • H. Nguyen, J. Yamagishi, I. Echizen
  • Computer Science, Engineering
  • ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
  • 2019
TLDR
The method introduced in this paper uses a capsule network to detect various kinds of spoofs, from replay attacks using printed images or recorded videos to computer-generated videos using deep convolutional neural networks. Expand
Face2Face Manipulation Detection Based on Histogram of Oriented Gradients
  • Amr Megahed, Q. Han
  • Computer Science
  • 2020 IEEE 19th International Conference on Trust, Security and Privacy in Computing and Communications (TrustCom)
  • 2020
TLDR
The proposed method utilizes the histogram of oriented gradients for feature extraction that can be effective in exposing Face2Face manipulations and effectively detects the manipulated faces with a high-performance accuracy under various compression quality levels. Expand
Detecting Manipulated Facial Videos: A Time Series Solution
We propose a new method to expose fake videos based on a time series solution. The method is based on bidirectional long short-term memory (Bi-LSTM) backbone architecture with two different types ofExpand
Detecting DeepFake, FaceSwap and Face2Face facial forgeries using frequency CNN
TLDR
A novel method that extracts faces from a target video and converts them into frequency domain using two dimensional global discrete Cosine transform (2D- GDCT) and employs a 3 layered frequency convolutional neural network to detect facial forgeries. Expand
Efficient-Frequency: a hybrid visual forensic framework for facial forgery detection
TLDR
This paper proposes a novel end-to-end visual forensic framework that can incorporate different modalities to efficiently classify real and forged contents and outperforms other state-of-the-art forensic approaches in many datasets and being robust to various visual forgery techniques. Expand
Video Transformer for Deepfake Detection with Incremental Learning
  • S. A. Khan, Hang Dai
  • Computer Science
  • ACM Multimedia
  • 2021
TLDR
The comprehensive experiments demonstrate that the proposed video transformer model with incremental learning achieves state-of-the-art performance in the deepfake video detection task with enhanced feature learning from the sequenced data. Expand
Deepfakes Detection with Automatic Face Weighting
TLDR
A method based on convolutional neural networks (CNNs) and recurrent neural Networks (RNNs) that extracts visual and temporal features from faces present in videos to accurately detect manipulations is introduced. Expand
Deep Learning model-based Multimedia forgery detection
TLDR
This paper portrays a technique to detect bogus content that will assist people in detecting bogus content and have confidence on the legitimacy of the content on the internet. Expand
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 34 REFERENCES
FaceForensics: A Large-scale Video Dataset for Forgery Detection in Human Faces
TLDR
A novel face manipulation dataset of about half a million edited images (from over 1000 videos) is introduced, which exceeds all existing video manipulation datasets by at least an order of magnitude and introduces benchmarks for classical image forensic tasks, including classification and segmentation. Expand
A deep learning approach to detection of splicing and copy-move forgeries in images
  • Y. Rao, J. Ni
  • Computer Science
  • 2016 IEEE International Workshop on Information Forensics and Security (WIFS)
  • 2016
TLDR
A new image forgery detection method based on deep learning technique, which utilizes a convolutional neural network to automatically learn hierarchical representations from the input RGB color images to outperforms some state-of-the-art methods. Expand
A Deep Learning Approach to Universal Image Manipulation Detection Using a New Convolutional Layer
TLDR
A universal forensic approach to performing manipulation detection using deep learning that can automatically learn how to detect multiple image manipulations without relying on pre-selected features or any preprocessing is proposed. Expand
An overview on video forensics
TLDR
The paper aims at providing an overview of the existing video processing techniques, considering all the possible alterations that can be operated on a single signal and also the possibility of identifying the traces that could reveal important information about its origin and use. Expand
Digital image forensics: a booklet for beginners
TLDR
This survey is designed for scholars and IT professionals approaching this field, reviewing existing tools and providing a view on the past, the present and the future of digital image forensics. Expand
Automatic Face Reenactment
We propose an image-based, facial reenactment system that replaces the face of an actor in an existing target video with the face of a user from a source video, while preserving the original targetExpand
Exposing digital forgeries in video by detecting double MPEG compression
TLDR
It is shown how a doublycompressed MPEG video sequence introduces specific static and temporal statistical perturbations whose presence can be used as evidence of tampering. Expand
Detecting Re-projected Video
TLDR
This work describes an automatic technique for detecting a video that was recorded from a screen and shows that the internal camera parameters of such video are inconsistent with the expected parameters of an authentic video. Expand
Screenshot identification using combing artifact from interlaced video
TLDR
A screenshot identification scheme using unique characteristic of interlaced video, combing artifact that performs well under the widely used image formats as JPEG, BMP, TIFF and video formats as MPEG-2, MPEG-4, H.264. Expand
A Survey of Image Forgery Detection
We are undoubtedly living in an age where we are exposed to a remarkable array of visual imagery. While we may have historically had confidence in the integrity of this imagery, today’s digitalExpand
...
1
2
3
4
...