Countering Malicious DeepFakes: Survey, Battleground, and Horizon

Abstract

The creation and the 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 (i.e., DeepFake generation and detection) 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 191 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 re-

A comprehensive survey on semantic facial attribute editing using generative adversarial networks

“…So, prominent studies have been done on GAN-based models for deepfake generation and detection. [70,154] have covered the recent techniques for manipulating face images. These studies have divided deepfake approaches into four groups including entire face synthesis, identity swap, attribute manipulation, and expression swap.…”

GAN-generated Faces Detection: A Survey and New Perspectives

“…Furthermore, the GAN-face detection task is closely related to other fake face detection tasks including morphed face detection and manipulated face detection. We also list related survey papers that focus on detecting face manipulation [Tolosana et al, 2020;Juefei-Xu et al, 2021;Nguyen et al, 2019], DeepFake [Lyu, 2020;Verdoliva, 2020], human visual performance of DeepFake [Khodabakhsh et al, 2019], Face Morphing [Pikoulis et al, 2021], etc.…”

A Review of Deep Learning-based Approaches for Deepfake Content Detection

“…Yadav and Salmani [7] proposed a survey on facial forgery techniques using generative adversarial networks, while Nguyen et al [8] excerpted the most relevant approaches for deepfake creation and detection [8]. Later on, Tolosana et al [9] provided a review on face manipulation and deepfake detection, and more recently Juefei-Xu et al [10] provided a deepfake-related study exposing the battleground between deepfake generation and detection and some insights regarding tendencies and future work. Finally, Mirsky et al [11] presented an illustrated catalog of the deepfake network architectures, also exploring the current status and tendencies of the attacker-defender game.…”

“…UADFVThe UADFV[70] is a synthetic dataset provided by the University of Albany with the primary objective of helping to detect fake face videos through physiological signals, i.e., eye blinking, a feature claimed by the authors as not well presented in synthesized videos. The dataset is composed of 49 fake videos generated through the FakeApp mobile application10 , where the individual's original faces are swapped with Nicolas Cage's face. Each sequence comprises a 294 × 500 pixels resolution and 11.14 seconds on average.…”