The MeVer DeepFake Detection Service: Lessons Learnt from Developing and Deploying in the Wild
Open Access
- 27 June 2022
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 59-68
Abstract
Enabled by recent improvements in generation methodologies, DeepFakes have become mainstream due to their increasingly better visual quality, the increase in easy-to-use generation tools and the rapid dissemination through social media. This fact poses a severe threat to our societies with the potential to erode social cohesion and influence our democracies. To mitigate the threat, numerous DeepFake detection schemes have been introduced in the literature but very few provide a web service that can be used in the wild. In this paper, we introduce the MeVer DeepFake detection service, a web service detecting deep learning manipulations in images and video. We present the design and implementation of the proposed processing pipeline that involves a model ensemble scheme, and we endow the service with a model card for transparency. Experimental results show that our service performs robustly on the three benchmark datasets while being vulnerable to Adversarial Attacks. Finally, we outline our experience and lessons learned when deploying a research system into production in the hopes that it will be useful to other academic and industry teams.Keywords
Funding Information
- US Department of State Global Engagement Center (SGECPD18CA0024)
- European Commission (951911)
This publication has 34 references indexed in Scilit:
- Capsule-forensics: Using Capsule Networks to Detect Forged Images and Videos2019
- Model Cards for Model Reporting2019
- Fake Face Detection Methods: Can They Be Generalized?2018
- Deep learning for self-driving cars2018
- The InVID Plug-in2017
- Synthesizing ObamaACM Transactions on Graphics, 2017
- Xception: Deep Learning with Depthwise Separable Convolutions2017
- Demo of Face2Face2016
- Deep Residual Learning for Image Recognition2016
- ImageNet: A large-scale hierarchical image database2009