Contrastive learning has delivered impressive results for various tasks in the self-supervised regime. However, existing approaches optimize for learning representations specific to downstream scenarios, i.e., \textit{global} representations suitable for tasks such as classification or \textit{local} representations for tasks such as detection and localization. While they produce satisfactory results in the intended downstream scenarios, they often fail to generalize to tasks that they were not originally designed for. In this work, we propose to learn video representations that generalize to both the tasks which require global semantic information (e.g., classification) and the tasks that require local fine-grained spatio-temporal information (e.g., localization). We achieve this by optimizing two contrastive objectives that together encourage our model to learn global-local visual information given audio signals. We show that the two objectives mutually improve the generalizability of the learned global-local representations, significantly outperforming their disjointly learned counterparts. We demonstrate our approach on various tasks including action/sound classification, lip reading, deepfake detection, event and sound localization (https://github.com/yunyikristy/global\_local).
This paper introduces a novel dataset to help researchers evaluate their computer vision and audio models for accuracy across a diverse set of age, genders, apparent skin tones and ambient lighting conditions. Our dataset is composed of 3,011 subjects and contains over 45,000 videos, with an average of 15 videos per person. The videos were recorded in multiple U.S. states with a diverse set of adults in various age, gender and apparent skin tone groups. A key feature is that each subject agreed to participate for their likenesses to be used. Additionally, our age and gender annotations are provided by the subjects themselves. A group of trained annotators labeled the subjects' apparent skin tone using the Fitzpatrick skin type scale. Moreover, annotations for videos recorded in low ambient lighting are also provided. As an application to measure robustness of predictions across certain attributes, we provide a comprehensive study on the top five winners of the DeepFake Detection Challenge (DFDC). Experimental evaluation shows that the winning models are less performant on some specific groups of people, such as subjects with darker skin tones and thus may not generalize to all people. In addition, we also evaluate the state-of-the-art apparent age and gender classification methods. Our experiments provides a thorough analysis on these models in terms of fair treatment of people from various backgrounds.
Deepfake is the manipulated video made with a generative deep learning technique such as Generative Adversarial Networks (GANs) or Auto Encoder that anyone can utilize. Recently, with the increase of Deepfake videos, some classifiers consisting of the convolutional neural network that can distinguish fake videos as well as deepfake datasets have been actively created. However, the previous studies based on the CNN structure have the problem of not only overfitting, but also considerable misjudging fake video as real ones. In this paper, we propose a Vision Transformer model with distillation methodology for detecting fake videos. We design that a CNN features and patch-based positioning model learns to interact with all positions to find the artifact region for solving false negative problem. Through comparative analysis on Deepfake Detection (DFDC) Dataset, we verify that the proposed scheme with patch embedding as input outperforms the state-of-the-art using the combined CNN features. Without ensemble technique, our model obtains 0.978 of AUC and 91.9 of f1 score, while previous SOTA model yields 0.972 of AUC and 90.6 of f1 score on the same condition.
With the progress in AI-based facial forgery (i.e., deepfake), people are increasingly concerned about its abuse. Albeit effort has been made for training classification (also known as deepfake detection) models to recognize such forgeries, existing models suffer from poor generalization to unseen forgery technologies and high sensitivity to changes in image/video quality. In this paper, we advocate adversarial training for improving the generalization ability to both unseen facial forgeries and unseen image/video qualities. We believe training with samples that are adversarially crafted to attack the classification models improves the generalization ability considerably. Considering that AI-based face manipulation often leads to high-frequency artifacts that can be easily spotted by models yet difficult to generalize, we further propose a new adversarial training method that attempts to blur out these specific artifacts, by introducing pixel-wise Gaussian blurring models. With adversarial training, the classification models are forced to learn more discriminative and generalizable features, and the effectiveness of our method can be verified by plenty of empirical evidence. Our code will be made publicly available.
A variety of effective face-swap and face-reenactment methods have been publicized in recent years, democratizing the face synthesis technology to a great extent. Videos generated as such have come to be called deepfakes with a negative connotation, for various social problems they have caused. Facing the emerging threat of deepfakes, we have built the Korean DeepFake Detection Dataset (KoDF), a large-scale collection of synthesized and real videos focused on Korean subjects. In this paper, we provide a detailed description of methods used to construct the dataset, experimentally show the discrepancy between the distributions of KoDF and existing deepfake detection datasets, and underline the importance of using multiple datasets for real-world generalization. KoDF is publicly available at https://moneybrain-research.github.io/kodf in its entirety (i.e. real clips, synthesized clips, clips with adversarial attack, and metadata).
A light-weight high-performance Deepfake detection method, called DefakeHop, is proposed in this work. State-of-the-art Deepfake detection methods are built upon deep neural networks. DefakeHop extracts features automatically using the successive subspace learning (SSL) principle from various parts of face images. The features are extracted by c/w Saab transform and further processed by our feature distillation module using spatial dimension reduction and soft classification for each channel to get a more concise description of the face. Extensive experiments are conducted to demonstrate the effectiveness of the proposed DefakeHop method. With a small model size of 42,845 parameters, DefakeHop achieves state-of-the-art performance with the area under the ROC curve (AUC) of 100%, 94.95%, and 90.56% on UADFV, Celeb-DF v1 and Celeb-DF v2 datasets, respectively.
AI-manipulated videos, commonly known as deepfakes, are an emerging problem. Recently, researchers in academia and industry have contributed several (self-created) benchmark deepfake datasets, and deepfake detection algorithms. However, little effort has gone towards understanding deepfake videos in the wild, leading to a limited understanding of the real-world applicability of research contributions in this space. Even if detection schemes are shown to perform well on existing datasets, it is unclear how well the methods generalize to real-world deepfakes. To bridge this gap in knowledge, we make the following contributions: First, we collect and present the largest dataset of deepfake videos in the wild, containing 1,869 videos from YouTube and Bilibili, and extract over 4.8M frames of content. Second, we present a comprehensive analysis of the growth patterns, popularity, creators, manipulation strategies, and production methods of deepfake content in the real-world. Third, we systematically evaluate existing defenses using our new dataset, and observe that they are not ready for deployment in the real-world. Fourth, we explore the potential for transfer learning schemes and competition-winning techniques to improve defenses.
Face forgery by deepfake is widely spread over the internet and has raised severe societal concerns. Recently, how to detect such forgery contents has become a hot research topic and many deepfake detection methods have been proposed. Most of them model deepfake detection as a vanilla binary classification problem, i.e, first use a backbone network to extract a global feature and then feed it into a binary classifier (real/fake). But since the difference between the real and fake images in this task is often subtle and local, we argue this vanilla solution is not optimal. In this paper, we instead formulate deepfake detection as a fine-grained classification problem and propose a new multi-attentional deepfake detection network. Specifically, it consists of three key components: 1) multiple spatial attention heads to make the network attend to different local parts; 2) textural feature enhancement block to zoom in the subtle artifacts in shallow features; 3) aggregate the low-level textural feature and high-level semantic features guided by the attention maps. Moreover, to address the learning difficulty of this network, we further introduce a new regional independence loss and an attention guided data augmentation strategy. Through extensive experiments on different datasets, we demonstrate the superiority of our method over the vanilla binary classifier counterparts, and achieve state-of-the-art performance.
In recent years, the advent of deep learning-based techniques and the significant reduction in the cost of computation resulted in the feasibility of creating realistic videos of human faces, commonly known as DeepFakes. The availability of open-source tools to create DeepFakes poses as a threat to the trustworthiness of the online media. In this work, we develop an open-source online platform, known as DeepFake-o-meter, that integrates state-of-the-art DeepFake detection methods and provide a convenient interface for the users. We describe the design and function of DeepFake-o-meter in this work.
Easy access to audio-visual content on social media, combined with the availability of modern tools such as Tensorflow or Keras, open-source trained models, and economical computing infrastructure, and the rapid evolution of deep-learning (DL) methods, especially Generative Adversarial Networks (GAN), have made it possible to generate deepfakes to disseminate disinformation, revenge porn, financial frauds, hoaxes, and to disrupt government functioning. The 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 for both audio and visual deepfakes. For each category of deepfake, we discuss information related to manipulation approaches, current public datasets, and key standards for the performance evaluation of deepfake detection techniques along with their results. Additionally, we also discuss open challenges and enumerate future directions to guide future researchers on issues that need to be considered to improve the domains of both deepfake generation and detection. This work is expected to assist the readers in understanding the creation and detection mechanisms of deepfakes, along with their current limitations and future direction.
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.
The rapid advancement of deep learning models that can generate and synthesis hyper-realistic videos known as Deepfakes and their ease of access to the general public have raised concern from all concerned bodies to their possible malicious intent use. Deep learning techniques can now generate faces, swap faces between two subjects in a video, alter facial expressions, change gender, and alter facial features, to list a few. These powerful video manipulation methods have potential use in many fields. However, they also pose a looming threat to everyone if used for harmful purposes such as identity theft, phishing, and scam. In this work, we propose a Convolutional Vision Transformer for the detection of Deepfakes. The Convolutional Vision Transformer has two components: Convolutional Neural Network (CNN) and Vision Transformer (ViT). The CNN extracts learnable features while the ViT takes in the learned features as input and categorizes them using an attention mechanism. We trained our model on the DeepFake Detection Challenge Dataset (DFDC) and have achieved 91.5 percent accuracy, an AUC value of 0.91, and a loss value of 0.32. Our contribution is that we have added a CNN module to the ViT architecture and have achieved a competitive result on the DFDC dataset.
The creation of altered and manipulated faces has become more common due to the improvement of DeepFake generation methods. Simultaneously, we have seen detection models' development for differentiating between a manipulated and original face from image or video content. In this paper, we focus on identifying the limitations and shortcomings of existing deepfake detection frameworks. We identified some key problems surrounding deepfake detection through quantitative and qualitative analysis of existing methods and datasets. We found that deepfake datasets are highly oversampled, causing models to become easily overfitted. The datasets are created using a small set of real faces to generate multiple fake samples. When trained on these datasets, models tend to memorize the actors' faces and labels instead of learning fake features. To mitigate this problem, we propose a simple data augmentation method termed Face-Cutout. Our method dynamically cuts out regions of an image using the face landmark information. It helps the model selectively attend to only the relevant regions of the input. Our evaluation experiments show that Face-Cutout can successfully improve the data variation and alleviate the problem of overfitting. Our method achieves a reduction in LogLoss of 15.2% to 35.3% on different datasets, compared to other occlusion-based techniques. Moreover, we also propose a general-purpose data pre-processing guideline to train and evaluate existing architectures allowing us to improve the generalizability of these models for deepfake detection.
Deepfakes are synthetically generated images, videos or audios, which fraudsters use to manipulate legitimate information. Current deepfake detection systems struggle against unseen data. To address this, we employ three different deep Convolutional Neural Network (CNN) models, (1) VGG16, (2) InceptionV3, and (3) XceptionNet to classify fake and real images extracted from videos. We also constructed a fusion of the deep CNN models to improve the robustness and generalisation capability. The proposed technique outperforms state-of-the-art models with 96.5% accuracy, when tested on publicly available DeepFake Detection Challenge (DFDC) test data, comprising of 400 videos. The fusion model achieves 99% accuracy on lower quality DeepFake-TIMIT dataset videos and 91.88% on higher quality DeepFake-TIMIT videos. In addition to this, we prove that prediction fusion is more robust against adversarial attacks. If one model is compromised by an adversarial attack, the prediction fusion does not let it affect the overall classification.
Synthetic media detection technologies label media as either synthetic or non-synthetic and are increasingly used by journalists, web platforms, and the general public to identify misinformation and other forms of problematic content. As both well-resourced organizations and the non-technical general public generate more sophisticated synthetic media, the capacity for purveyors of problematic content to adapt induces a \newterm{detection dilemma}: as detection practices become more accessible, they become more easily circumvented. This paper describes how a multistakeholder cohort from academia, technology platforms, media entities, and civil society organizations active in synthetic media detection and its socio-technical implications evaluates the detection dilemma. Specifically, we offer an assessment of detection contexts and adversary capacities sourced from the broader, global AI and media integrity community concerned with mitigating the spread of harmful synthetic media. A collection of personas illustrates the intersection between unsophisticated and highly-resourced sponsors of misinformation in the context of their technical capacities. This work concludes that there is no "best" approach to navigating the detector dilemma, but derives a set of implications from multistakeholder input to better inform detection process decisions and policies, in practice.
To properly contrast the Deepfake phenomenon the need to design new Deepfake detection algorithms arises; the misuse of this formidable A.I. technology brings serious consequences in the private life of every involved person. State-of-the-art proliferates with solutions using deep neural networks to detect a fake multimedia content but unfortunately these algorithms appear to be neither generalizable nor explainable. However, traces left by Generative Adversarial Network (GAN) engines during the creation of the Deepfakes can be detected by analyzing ad-hoc frequencies. For this reason, in this paper we propose a new pipeline able to detect the so-called GAN Specific Frequencies (GSF) representing a unique fingerprint of the different generative architectures. By employing Discrete Cosine Transform (DCT), anomalous frequencies were detected. The \BETA statistics inferred by the AC coefficients distribution have been the key to recognize GAN-engine generated data. Robustness tests were also carried out in order to demonstrate the effectiveness of the technique using different attacks on images such as JPEG Compression, mirroring, rotation, scaling, addition of random sized rectangles. Experiments demonstrated that the method is innovative, exceeds the state of the art and also give many insights in terms of explainability.
Images synthesized by powerful generative adversarial network (GAN) based methods have drawn moral and privacy concerns. Although image forensic models have reached great performance in detecting fake images from real ones, these models can be easily fooled with a simple adversarial attack. But, the noise adding adversarial samples are also arousing suspicion. In this paper, instead of adding adversarial noise, we optimally search adversarial points on face manifold to generate anti-forensic fake face images. We iteratively do a gradient-descent with each small step in the latent space of a generative model, e.g. Style-GAN, to find an adversarial latent vector, which is similar to norm-based adversarial attack but in latent space. Then, the generated fake images driven by the adversarial latent vectors with the help of GANs can defeat main-stream forensic models. For examples, they make the accuracy of deepfake detection models based on Xception or EfficientNet drop from over 90% to nearly 0%, meanwhile maintaining high visual quality. In addition, we find manipulating style vector $z$ or noise vectors $n$ at different levels have impacts on attack success rate. The generated adversarial images mainly have facial texture or face attributes changing.
In recent years, the abuse of a face swap technique called deepfake has raised enormous public concerns. So far, a large number of deepfake videos (known as "deepfakes") have been crafted and uploaded to the internet, calling for effective countermeasures. One promising countermeasure against deepfakes is deepfake detection. Several deepfake datasets have been released to support the training and testing of deepfake detectors, such as DeepfakeDetection and FaceForensics++. While this has greatly advanced deepfake detection, most of the real videos in these datasets are filmed with a few volunteer actors in limited scenes, and the fake videos are crafted by researchers using a few popular deepfake softwares. Detectors developed on these datasets may become less effective against real-world deepfakes on the internet. To better support detection against real-world deepfakes, in this paper, we introduce a new dataset WildDeepfake which consists of 7,314 face sequences extracted from 707 deepfake videos collected completely from the internet. WildDeepfake is a small dataset that can be used, in addition to existing datasets, to develop and test the effectiveness of deepfake detectors against real-world deepfakes. We conduct a systematic evaluation of a set of baseline detection networks on both existing and our WildDeepfake datasets, and show that WildDeepfake is indeed a more challenging dataset, where the detection performance can decrease drastically. We also propose two (eg. 2D and 3D) Attention-based Deepfake Detection Networks (ADDNets) to leverage the attention masks on real/fake faces for improved detection. We empirically verify the effectiveness of ADDNets on both existing datasets and WildDeepfake. The dataset is available at: https://github.com/OpenTAI/wild-deepfake.
Existing deepfake detection methods have reported promising in-distribution results, by accessing published large-scale dataset. However, due to the non-smooth synthesis method, the fake samples in this dataset may expose obvious artifacts (e.g., stark visual contrast, non-smooth boundary), which were heavily relied on by most of the frame-level detection methods above. As these artifacts do not come up in real media forgeries, the above methods can suffer from a large degradation when applied to fake images that close to reality. To improve the robustness for high-realism fake data, we propose the Invariant Texture Learning (InTeLe) framework, which only accesses the published dataset with low visual quality. Our method is based on the prior that the microscopic facial texture of the source face is inevitably violated by the texture transferred from the target person, which can hence be regarded as the invariant characterization shared among all fake images. To learn such an invariance for deepfake detection, our InTeLe introduces an auto-encoder framework with different decoders for pristine and fake images, which are further appended with a shallow classifier in order to separate out the obvious artifact-effect. Equipped with such a separation, the extracted embedding by encoder can capture the texture violation in fake images, followed by the classifier for the final pristine/fake prediction. As a theoretical guarantee, we prove the identifiability of such an invariance texture violation, i.e., to be precisely inferred from observational data. The effectiveness and utility of our method are demonstrated by promising generalization ability from low-quality images with obvious artifacts to fake images with high realism.
Designed to learn long-range interactions on sequential data, transformers continue to show state-of-the-art results on a wide variety of tasks. In contrast to CNNs, they contain no inductive bias that prioritizes local interactions. This makes them expressive, but also computationally infeasible for long sequences, such as high-resolution images. We demonstrate how combining the effectiveness of the inductive bias of CNNs with the expressivity of transformers enables them to model and thereby synthesize high-resolution images. We show how to (i) use CNNs to learn a context-rich vocabulary of image constituents, and in turn (ii) utilize transformers to efficiently model their composition within high-resolution images. Our approach is readily applied to conditional synthesis tasks, where both non-spatial information, such as object classes, and spatial information, such as segmentations, can control the generated image. In particular, we present the first results on semantically-guided synthesis of megapixel images with transformers and obtain the state of the art among autoregressive models on class-conditional ImageNet. Code and pretrained models can be found at https://github.com/CompVis/taming-transformers .