Countering Malicious DeepFakes: Survey, Battleground, and Horizon

View on arXiv ← Back to list

Authors: Felix Juefei-Xu, Run Wang, Yihao Huang, Qing Guo, Lei Ma, Yang Liu

Published: 2021-02-27 13:48:54+00:00

AI Summary

This paper presents a comprehensive survey of DeepFake generation and detection research, analyzing the interplay between the two fields (a "battleground"). It categorizes DeepFake generation and detection methods, visually representing their interactions, and identifies challenges and future research directions.

Abstract

The creation or manipulation of facial appearance through deep generative approaches, known as DeepFake, have achieved significant progress and promoted a wide range of benign and malicious applications, e.g., visual effect assistance in movie and misinformation generation by faking famous persons. The evil side of this new technique poses another popular study, i.e., DeepFake detection aiming to identify the fake faces from the real ones. With the rapid development of the DeepFake-related studies in the community, both sides have formed the relationship of battleground, pushing the improvements of each other and inspiring new directions, e.g., the evasion of DeepFake detection. Nevertheless, the overview of such battleground and the new direction is unclear and neglected by recent surveys due to the rapid increase of related publications, limiting the in-depth understanding of the tendency and future works. To fill this gap, in this paper, we provide a comprehensive overview and detailed analysis of the research work on the topic of DeepFake generation, DeepFake detection as well as evasion of DeepFake detection, with more than 318 research papers carefully surveyed. We present the taxonomy of various DeepFake generation methods and the categorization of various DeepFake detection methods, and more importantly, we showcase the battleground between the two parties with detailed interactions between the adversaries (DeepFake generation) and the defenders (DeepFake detection). The battleground allows fresh perspective into the latest landscape of the DeepFake research and can provide valuable analysis towards the research challenges and opportunities as well as research trends and future directions. We also elaborately design interactive diagrams (http://www.xujuefei.com/dfsurvey) to allow researchers to explore their own interests on popular DeepFake generators or detectors.

Key findings

DeepFake detection methods heavily rely on curated datasets; generalization and robustness against adversarial attacks remain key challenges; biological signals are emerging as promising detection cues; the field is rapidly evolving, requiring continuous updates to datasets and evaluation methods.

Approach

The authors surveyed over 318 research papers on DeepFake generation, detection, and evasion. They categorized methods, visualized their interactions using Sankey and chord diagrams, and analyzed trends to identify challenges and future research directions.

Datasets

CASIA-WebFace, CelebA, VGGFace, MegaFace, LSUN, MS-Celeb-1M, VGGFace2, Flickr-Faces-HQ, UADFV, DeepFake-TIMIT, DFDC Preview, Google DFD, FaceForensics++, Celeb-DF, DFFD, FakeCatcher, iFakeFaceDB, DFDC, Vox-DeepFake, DeeperForensics-1.0, WildDeepFake, ForgeryNet, DF-W, FFIW10K, OpenForensics

Model(s)

Various CNN architectures (ResNet, EfficientNet, XceptionNet), GANs (DCGAN, WGAN, PGGAN, StyleGAN), VAEs, RNNs, LSTMs, HMN, Gram-Net, HRNet, etc. The survey focuses on the methods used rather than a specific model.

Author countries

USA, China, Singapore, Canada

← Previous