Improving the Efficiency and Robustness of Deepfakes Detection through Precise Geometric Features

  title={Improving the Efficiency and Robustness of Deepfakes Detection through Precise Geometric Features},
  author={Zekun Sun and Yujie Han and Zeyu Hua and Na Ruan and Weijia Jia},
  journal={2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  • Zekun Sun, Yujie Han, +2 authors Weijia Jia
  • Published 9 April 2021
  • Computer Science
  • 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Deepfakes is a branch of malicious techniques that transplant a target face to the original one in videos, resulting in serious problems such as infringement of copyright, confusion of information, or even public panic. Previous efforts for Deepfakes videos detection mainly focused on appearance features, which have a risk of being bypassed by sophisticated manipulation, also resulting high model complexity and sensitiveness to noise. Besides, how to mine the temporal features of manipulated… Expand


Recurrent Convolutional Strategies for Face Manipulation Detection in Videos
This work attempts to detect Deepfake, Face2Face and FaceSwap tampered faces in video streams using recurrent convolutional models and distill the best strategy for combining variations in these models along with domain specific face preprocessing techniques through extensive experimentation to obtain state-of-the-art performance on publicly available video-based facial manipulation benchmarks. Expand
Exposing DeepFake Videos By Detecting Face Warping Artifacts
A new deep learning based method that can effectively distinguish AI-generated fake videos from real videos is described, which saves a plenty of time and resources in training data collection and is more robust compared to others. Expand
Detection of Deep Network Generated Images Using Disparities in Color Components
The proposed feature set to capture color image statistics for detecting deep network generated (DNG) images is proposed and experimental results show that the proposed method is able to distinguish the DNG images from real ones with high accuracies. Expand
Deepfake Video Detection Using Recurrent Neural Networks
  • David Guera, E. Delp
  • Computer Science
  • 2018 15th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS)
  • 2018
A temporal-aware pipeline to automatically detect deepfake videos is proposed that uses a convolutional neural network to extract frame-level features and a recurrent neural network that learns to classify if a video has been subject to manipulation or not. 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
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
MesoNet: a Compact Facial Video Forgery Detection Network
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. Expand
FaceForensics++: Learning to Detect Manipulated Facial Images
This paper proposes an automated benchmark for facial manipulation detection, and shows that the use of additional domain-specific knowledge improves forgery detection to unprecedented accuracy, even in the presence of strong compression, and clearly outperforms human observers. Expand
Celeb-DF: A Large-Scale Challenging Dataset for DeepFake Forensics
This work presents a new large-scale challenging DeepFake video dataset, Celeb-DF, which contains 5,639 high-quality DeepFake videos of celebrities generated using improved synthesis process and conducts a comprehensive evaluation of DeepFake detection methods and datasets to demonstrate the escalated level of challenges posed by Celebrity-DF. Expand
Temporal Segment Networks: Towards Good Practices for Deep Action Recognition
Deep convolutional networks have achieved great success for visual recognition in still images. However, for action recognition in videos, the advantage over traditional methods is not so evident.Expand
Learning Spatiotemporal Features with 3D Convolutional Networks
The learned features, namely C3D (Convolutional 3D), with a simple linear classifier outperform state-of-the-art methods on 4 different benchmarks and are comparable with current best methods on the other 2 benchmarks. Expand