MesoNet: a Compact Facial Video Forgery Detection Network

Abstract : 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. Traditional image forensics techniques are usually not well suited to videos due to the compression that strongly degrades the data. Thus, this paper follows a deep learning approach and presents two networks, both with a low number of layers to focus on the mesoscopic properties of images. We evaluate those fast networks on both an existing dataset and a dataset we have constituted from online videos. The tests demonstrate a very successful detection rate with more than 98% for Deepfake and 95% for Face2Face.
Complete list of metadatas

Cited literature [21 references]  Display  Hide  Download

https://hal-upec-upem.archives-ouvertes.fr/hal-01867298
Contributor : Vincent Nozick <>
Submitted on : Tuesday, September 4, 2018 - 11:15:02 AM
Last modification on : Friday, May 24, 2019 - 4:12:33 PM
Long-term archiving on : Wednesday, December 5, 2018 - 2:44:57 PM

File

afchar_WIFS_2018.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01867298, version 1
  • ARXIV : 1809.00888

Citation

Darius Afchar, Vincent Nozick, Junichi Yamagishi, Isao Echizen. MesoNet: a Compact Facial Video Forgery Detection Network. 2018. ⟨hal-01867298⟩

Share

Metrics

Record views

166

Files downloads

257