Toward the Creation and Obstruction of DeepFakes

Yuezun Li,Pu Sun,Siwei Lyu,Honggang Qi

doi:10.1007/978-3-030-87664-7_4

Abstract

AbstractAI-synthesized face-swapping videos, commonly known as DeepFakes, is an emerging problem threatening the trustworthiness of online information. The need to develop and evaluate DeepFake detection algorithms calls for large-scale datasets. However, current DeepFake datasets suffer from low visual quality and do not resemble DeepFake videos circulated on the Internet. We present a new large-scale challenging DeepFake video dataset, Celeb-DF, which contains 5, 639 high-quality DeepFake videos of celebrities generated using an improved synthesis process. We conduct a comprehensive evaluation of DeepFake detection methods and datasets to demonstrate the escalated level of challenges posed by Celeb-DF. Then we introduce Landmark Breaker, the first dedicated method to disrupt facial landmark extraction, and apply it to the obstruction of the generation of DeepFake videos. The experiments are conducted on three state-of-the-art facial landmark extractors using our Celeb-DF dataset.

Highlights

A recent twist to the disconcerting problem of online disinformation is falsified videos created by AI technologies, in particular, deep neural networks (DNNs)
We can observe the Base1 method merely has any effect on the Normalized Mean Error (NME) performance but can largely degrade the quality of adversarial images compared to Base2 and Landmark Breaker (LB)
The Base2 method can achieve the competitive performance with Landmark Breaker in NME but is slightly degraded in Structural Similarity (SSIM)

Summary

Introduction

A recent twist to the disconcerting problem of online disinformation is falsified videos created by AI technologies, in particular, deep neural networks (DNNs). One particular type of DNN-based fake video, commonly known as DeepFakes, has recently drawn much attention. Since faces are intrinsically associated with identity, well-crafted DeepFakes can create illusions of a person’s presence and activities that do not occur in reality, which can lead to serious political, social, financial, and legal consequences [10]. With the escalated concerns over DeepFakes, there is a surge of interest in developing DeepFake detection methods recently [1, 18, 29, 30, 37, 40–42, 47, 48, 61], with an upcoming dedicated global DeepFake Detection Challenge.. We have the UADFV dataset [61], the DeepFake-TIMIT dataset (DF-TIMIT) [26], the FaceForensics++ dataset (FF-DF) [47]2, the Google DeepFake detection dataset (DFD) [14], and the Facebook DeepFake detection challenge (DFDC) dataset [12]

Objectives

Methods

Results

Conclusion