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 (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 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.
Deepfake videos are increasingly used in spreading fake news or propaganda having a serious impact on people and society. Traditional deepfake detectors exploit spatial and/or temporal ...inconsistencies to differentiate between real and fake videos. Owing to the rapidly advancing deepfake creation algorithms, the latest detectors have made use of physiological and biological facial features to create more generic solutions. Our proposed solution uses facial landmarks as the physiological identifiers of a person’s face and through them develops a relationship between facial areas in normal speech and tampered speech. By creating a graph structure from the resulting sparse data, we were able to use a spatio-temporal graph convolutional network for classification, which has significantly fewer parameters and a shorter training time than traditional CNNs. We conducted a multitude of experiments on 3 datasets, utilizing spatio-temporal features. The results demonstrate that this technique has better generalization, and high performance compared to latest research in deepfake detection without the reliance on large deep learning models which are tuned to learning image discrepancies more than data patterns. Moreover, our use of facial landmark-based features with a graph structure paves the way for the development of an explainable AI model that can be relied on.
•Deepfake video generation algorithms modify the data associated with facial landmarks to create fake images and videos which are used as a source for spreading fake news.•Facial landmarks represent an important structural representation of the face.•A feature vector can be found on each facial landmark to create a representation of the facial structure.•Facial structural data in form of landmarks and feature vectors can be classified using Graph CNNs to detect deepfakes since GCNs are better suited for sparse geometric data.
With the continuous improvements of deepfake methods, forgery messages have transitioned from single-modality to multi-modal fusion, posing new challenges for existing forgery detection algorithms. ...In this letter, we propose AVT<inline-formula><tex-math notation="LaTeX">^{2}</tex-math></inline-formula>-DWF , the A udio- V isual dual T ransformers grounded in D ynamic W eight F usion, which aims to amplify both intra- and cross-modal forgery cues, thereby enhancing detection capabilities. AVT<inline-formula><tex-math notation="LaTeX">^{2}</tex-math></inline-formula>-DWF adopts a dual-stage approach to capture both spatial characteristics and temporal dynamics of facial expressions. This is achieved through a face transformer with an <inline-formula><tex-math notation="LaTeX">n</tex-math></inline-formula>-frame-wise tokenization strategy encoder and an audio transformer encoder. Subsequently, it uses multi-modal conversion with dynamic weight fusion to address the challenge of heterogeneous information fusion between audio and visual modalities. Experiments on DeepfakeTIMIT, FakeAVCeleb, and DFDC datasets indicate that AVT<inline-formula><tex-math notation="LaTeX">^{2}</tex-math></inline-formula>-DWF achieves state-of-the-art performance intra- and cross-dataset Deepfake detection.
Deepfake techniques can forge the visual or audio signals in the video, which leads to inconsistencies between visual and audio (VA) signals. Therefore, multimodal detection methods expose deepfake ...videos by extracting VA inconsistencies. Recently, deepfake technology has started VA collaborative forgery to obtain more realistic deepfake videos, which poses new challenges for extracting VA inconsistencies. Recent multimodal detection methods propose to first extract natural VA correspondences in real videos in a self-supervised manner, and then use the learned real correspondences as targets to guide the extraction of VA inconsistencies in the subsequent deepfake detection stage. However, the inherent VA relations are difficult to extract due to the modality gap, which leads to the limited auxiliary performance of the aforementioned self-supervised methods. In this paper, we propose Predictive Visual-audio Alignment Self-supervision for Multimodal Deepfake Detection (PVASS-MDD), which consists of PVASS auxiliary and MDD stages. In the PVASS auxiliary stage in real videos, we first devise a three-stream network to associate two augmented visual views with corresponding audio clues, leading to explore common VA correspondences based on cross-view learning. Secondly, we introduce a novel cross-modal predictive align module for eliminating VA gaps to provide inherent VA correspondences. In the MDD stage, we propose to the auxiliary loss to utilize the frozen PVASS network to align VA features of real videos, to better assist multimodal deepfake detector for capturing subtle VA inconsistencies. We conduct extensive experiments on existing widely used and latest multimodal deepfake datasets. Our method obtains a significant performance improvement compared to state-of-the-art methods.
Recent studies have shown that lip shape and movement can be used as an effective biometric feature for speaker authentication. By using random prompt text scheme, lip-based authentication system can ...also achieve good liveness detection performance in laboratory scenarios. However, due to the increasingly widespread mobile application, the authentication system may face additional practical difficulties such as complex background, limited user samples, etc., which will degrade the authentication performance derived by current methods. To confront the above problems, a new deep neural network, i.e. the Triple-feature Disentanglement Network for Visual Speaker Authentication (TDVSA-Net), is proposed in this paper to extract discriminative and disentangled lip features for visual speaker authentication in the random prompt text scenario. Three decoupled lip features, including the content feature inferring the speech content, the physiological lip feature describing the static lip shape and appearance and the behavioral lip feature depicting the unique pattern in lip movements during utterance, are extracted by TDVSA-Net and fed into corresponding modules to authenticate both the prompt text and the speaker's identity. Experiment results have demonstrated that compared with several SOTA visual speaker authentication methods, the proposed TDVSA-Net can extract more discriminative and robust lip features which boost the content recognition and identity authentication performance against both human imposters and DeepFake attacks.
Easy access to audio-visual content on social media, combined with the availability of modern tools such as Tensorflow or Keras, and open-source trained models, along with economical computing ...infrastructure, and the rapid evolution of deep-learning (DL) methods have heralded a new and frightening trend. Particularly, the advent of easily available and ready to use Generative Adversarial Networks (GANs), have made it possible to generate deepfakes media partially or completely fabricated with the intent to deceive to disseminate disinformation and revenge porn, to perpetrate financial frauds and other hoaxes, and to disrupt government functioning. Existing surveys have mainly focused on the detection of deepfake images and videos; this paper provides a comprehensive review and detailed analysis of existing tools and machine learning (ML) based approaches for deepfake generation, and the methodologies used to detect such manipulations in both audio and video. For each category of deepfake, we discuss information related to manipulation approaches, current public datasets, and key standards for the evaluation of the performance of deepfake detection techniques, along with their results. Additionally, we also discuss open challenges and enumerate future directions to guide researchers on issues which need to be considered in order to improve the domains of both deepfake generation and detection. This work is expected to assist readers in understanding how deepfakes are created and detected, along with their current limitations and where future research may lead.
Traditionally, the production and distribution of advertising material has relied on human effort and analog tools. However, technological innovations have given the advertising industry digital and ...automatic tools that enable advertisers to automate many advertising processes and produce "synthetic ads," or ads comprising content based on the artificial and automatic production and modification of data. The emerging practice of synthetic advertising, to date the most sophisticated form of ad manipulation, relies on various artificial intelligence (AI) techniques, such as deepfakes and generative adversarial networks (GANs), to automatically create content that depicts an unreal, albeit convincing, artificial version of reality. In this article, a general framework is constructed to better understand how consumers respond to all forms of ad manipulation. It is anticipated that this article will help explain how consumers respond to the more sophisticated forms of synthetic ads-such as deepfakes-that are emerging at an accelerating rate. To guide research in this area, a research agenda is developed focusing on three manipulated advertising areas: ad falsity, consumer response, and originality. Furthermore, the implications for theory and industry are considered.
•DeepFakes and beyond: types of facial manipulations.•Facial manipulation techniques.•Databases for research in face manipulation and fake detection.•Key benchmarks for technology evaluation of fake ...detection methods.•Summary of fake detection results for each facial manipulation group.
The free access to large-scale public databases, together with the fast progress of deep learning techniques, in particular Generative Adversarial Networks, have led to the generation of very realistic fake content with its corresponding implications towards society in this era of fake news.
This survey provides a thorough review of techniques for manipulating face images including DeepFake methods, and methods to detect such manipulations. In particular, four types of facial manipulation are reviewed: i) entire face synthesis, ii) identity swap (DeepFakes), iii) attribute manipulation, and iv) expression swap. For each manipulation group, we provide details regarding manipulation techniques, existing public databases, and key benchmarks for technology evaluation of fake detection methods, including a summary of results from those evaluations. Among all the aspects discussed in the survey, we pay special attention to the latest generation of DeepFakes, highlighting its improvements and challenges for fake detection.
In addition to the survey information, we also discuss open issues and future trends that should be considered to advance in the field.
The present study examined individuals’ perceived message and video fakeness of deepfake (versus real) videos and deepfake-described (versus non-described) videos, and the moderating effect of ...perceived deepfake targeted politicians’ personality characteristics on the perceived fakeness of deepfake videos. Six hundred and one participants were randomly assigned to one of the four groups: deepfake-described deepfake videos (
n
= 148), non-described deepfake videos (
n
= 157), deepfake-described real videos (
n
= 143), and non-described real videos (
n
= 153). Participants in each group watched deepfake or real Trump and Obama videos, and then answered questions about their perceived fakeness of each video and the perceived dangerousness and trustworthiness of the video target. Results indicated that participants were able to make the correct decisions to perceive the deepfake and deepfake-described videos and messages as less realistic than real and non-described videos. As predicted by error management theory, participants were inclined to commit the less costly false positive error to perceive dangerous video targets’ messages in real and non-described videos as fake as deepfake and deepfake-described videos. In contrast, they were prone to make the less costly false negative error to perceive trustworthy video targets’ messages in deepfake videos, and the deepfake videos, as real as real videos. Theoretical and practical implications for deepfakes research were discussed.
Deepfakes: Vehicles for Radicalization, Not Persuasion Nieweglowska, Maja; Stellato, Cal; Sloman, Steven A.
Current directions in psychological science : a journal of the American Psychological Society,
06/2023, Volume:
32, Issue:
3
Journal Article
Peer reviewed
Deepfakes are an effective method of media manipulation because of their realism and also because truth is not a priority when people are consuming and sharing content online. Consumers are more ...focused on creating their own reality that aligns with their desires, opinions, and values. We explain how deepfakes differ from other sources of information. Their realism and vividness makes them unusually effective at depicting alternative facts, including fake news. Deepfakes are difficult to detect and will be even harder to detect in the future. However, people share deepfakes not necessarily because they believe them but because they want to reinforce their own identity and social position. The threat posed by deepfakes is that they can radicalize people by sowing chaos and confusion. They rarely change minds. We review the consequences of deepfakes in both the social sphere and private lives. We suggest potential solutions to reduce their negative consequences.