VideoFACT: Detecting Video Forgeries Using Attention, Scene Context, and Forensic Traces

@article{Nguyen2022VideoFACTDV,
  title={VideoFACT: Detecting Video Forgeries Using Attention, Scene Context, and Forensic Traces},
  author={Tai Duy Nguyen and Shengbang Fang and Matthew C. Stamm},
  journal={ArXiv},
  year={2022},
  volume={abs/2211.15775}
}
Fake videos represent an important misinformation threat. While existing forensic networks have demonstrated strong performance on image forgeries, recent results reported on the Adobe VideoSham dataset show that these networks fail to identify fake content in videos. In this paper, we show that this is due to video coding, which introduces local variation into forensic traces. In response, we propose VideoFACT - a new network that is able to detect and localize a wide variety of video… 
View PDF on arXiv

Figures and Tables from this paper

References

SHOWING 1-10 OF 88 REFERENCES

Detecting Tampered Videos with Multimedia Forensics and Deep Learning

This work presents an approach for automatic video manipulation detection inspired by manual verification approaches, and discovers that, while competing approaches perform better when trained with videos from the same dataset, one of the proposed filters demonstrates superior performance in cross-dataset settings.

Detection of GAN-Generated Fake Images over Social Networks

The diffusion of fake images and videos on social networks is a fast growing problem. Commercial media editing tools allow anyone to remove, add, or clone people and objects, to generate fake images.…

A C3D-Based Convolutional Neural Network for Frame Dropping Detection in a Single Video Shot

This paper proposes a new approach for forensic analysis by exploiting the local spatio-temporal relationships within a portion of a video to robustly detect frame removals and produces a refined video-level confidence score that is superior to the raw output scores from the network.

Deep Fake Image Detection Based on Pairwise Learning

This paper proposes a deep learning-based approach for detecting the fake images by using the contrastive loss and demonstrated that the proposed method significantly outperformed other state-of-the-art fake image detectors.

Video Face Manipulation Detection Through Ensemble of CNNs

This paper studies the ensembling of different trained Convolutional Neural Network (CNN) models and shows that combining these networks leads to promising face manipulation detection results on two publicly available datasets with more than 119000 videos.

Noiseprint: A CNN-Based Camera Model Fingerprint

This paper proposes a method to extract a camera model fingerprint, called noiseprint, where the scene content is largely suppressed and model-related artifacts are enhanced, by means of a Siamese network trained with pairs of image patches coming from the same or different cameras.

Forensic Similarity for Digital Images

A new digital image forensics approach called forensic similarity, which determines whether two image patches contain the same forensic trace or different forensic traces, is introduced and the utility of this approach is demonstrated in two practical applications: forgery detection and localization, and database consistency verification.

ManTra-Net: Manipulation Tracing Network for Detection and Localization of Image Forgeries With Anomalous Features

The forgery localization problem is formulated as a local anomaly detection problem, a Z-score feature is designed to capture local anomaly, and a novel long short-term memory solution is proposed to assess local anomalies.

Exposing Fake Images With Forensic Similarity Graphs

This paper introduces a novel graph-based representation of an image that captures key forensic relationships among regions in the image, which is called the Forensic Similarity Graph, and presents two community detection techniques, adapted from literature, to detect and localize image forgeries.

Detection of frame deletion for digital video forensics

...