The MeVer DeepFake Detection Service: Lessons Learnt from Developing and Deploying in the Wild

TL;DR

This paper presents the MeVer DeepFake detection web service, detailing its design, implementation, and deployment challenges, along with experimental results and lessons learned from real-world use.

Contribution

It introduces a robust DeepFake detection web service with a model ensemble and transparency features, and shares practical deployment insights.

Findings

Performs robustly on benchmark datasets

Vulnerable to Adversarial Attacks

Provides a transparent model card

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.