Skip to Main content Skip to Navigation
Conference papers

A video is worth more than 1000 lies. Comparing 3DCNN approaches for detecting deepfakes

Yaohui Wang 1 Antitza Dantcheva 1
1 STARS - Spatio-Temporal Activity Recognition Systems
CRISAM - Inria Sophia Antipolis - Méditerranée
Abstract : Manipulated images and videos have become increasingly realistic due to the tremendous progress of deep convolutional neural networks (CNNs). While technically intriguing , such progress raises a number of social concerns related to the advent and spread of fake information and fake news. Such concerns necessitate the introduction of robust and reliable methods for fake image and video detection. Towards this in this work, we study the ability of state of the art video CNNs including 3D ResNet, 3D ResNeXt, and I3D in detecting manipulated videos. We present related experimental results on videos tampered by four manipulation techniques, as included in the FaceForensics++ dataset. We investigate three scenarios, where the networks are trained to detect (a) all manipulated videos, as well as (b) separately each manipulation technique individually. Finally and deviating from previous works, we conduct cross-manipulation results, where we (c) detect the veracity of videos pertaining to manipulation-techniques not included in the train set. Our findings clearly indicate the need for a better understanding of manipulation methods and the importance of designing algorithms that can successfully generalize onto unknown manipulations.
Complete list of metadata

Cited literature [39 references]  Display  Hide  Download

https://hal.inria.fr/hal-02862476
Contributor : Antitza Dantcheva <>
Submitted on : Tuesday, June 9, 2020 - 3:29:46 PM
Last modification on : Wednesday, January 6, 2021 - 10:02:22 AM

File

fg_camera_ready.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-02862476, version 1

Collections

Citation

Yaohui Wang, Antitza Dantcheva. A video is worth more than 1000 lies. Comparing 3DCNN approaches for detecting deepfakes. FG 2020 - 15th IEEE International Conference on Automatic Face and Gesture Recognition, Nov 2020, Buenos Aires / Virtual, Argentina. ⟨hal-02862476⟩

Share

Metrics

Record views

318

Files downloads

975