Video DeepFakes are fake media created with Deep Learning (DL) that manipulate a person's expression or identity. Most current DeepFake detection methods analyze each frame independently, ignoring inconsistencies and unnatural movements between frames. Some newer methods employ optical flow models to capture this temporal aspect, but they are computationally expensive. In contrast, we propose using the related but often ignored Motion Vectors (MVs) and Information Masks (IMs) from the H.264 video codec, to detect temporal inconsistencies in DeepFakes. Our experiments show that this approach is effective and has minimal computational costs, compared with per-frame RGB-only methods. This could lead to new, real-time temporally-aware DeepFake detection methods for video calls and streaming.
DeepFake detection is pivotal in personal privacy and public safety. With the iterative advancement of DeepFake techniques, high-quality forged videos and images are becoming increasingly deceptive. Prior research has seen numerous attempts by scholars to incorporate biometric features into the field of DeepFake detection. However, traditional biometric-based approaches tend to segregate biometric features from general ones and freeze the biometric feature extractor. These approaches resulted in the exclusion of valuable general features, potentially leading to a performance decline and, consequently, a failure to fully exploit the potential of biometric information in assisting DeepFake detection. Moreover, insufficient attention has been dedicated to scrutinizing gaze authenticity within the realm of DeepFake detection in recent years. In this paper, we introduce GazeForensics, an innovative DeepFake detection method that utilizes gaze representation obtained from a 3D gaze estimation model to regularize the corresponding representation within our DeepFake detection model, while concurrently integrating general features to further enhance the performance of our model. Experiment results reveal that our proposed GazeForensics outperforms the current state-of-the-art methods.
The remarkable generative capabilities of denoising diffusion models have raised new concerns regarding the authenticity of the images we see every day on the Internet. However, the vast majority of existing deepfake detection models are tested against previous generative approaches (e.g. GAN) and usually provide only a "fake" or "real" label per image. We believe a more informative output would be to augment the per-image label with a localization map indicating which regions of the input have been manipulated. To this end, we frame this task as a weakly-supervised localization problem and identify three main categories of methods (based on either explanations, local scores or attention), which we compare on an equal footing by using the Xception network as the common backbone architecture. We provide a careful analysis of all the main factors that parameterize the design space: choice of method, type of supervision, dataset and generator used in the creation of manipulated images; our study is enabled by constructing datasets in which only one of the components is varied. Our results show that weakly-supervised localization is attainable, with the best performing detection method (based on local scores) being less sensitive to the looser supervision than to the mismatch in terms of dataset or generator.
Multimodal manipulations (also known as audio-visual deepfakes) make it difficult for unimodal deepfake detectors to detect forgeries in multimedia content. To avoid the spread of false propaganda and fake news, timely detection is crucial. The damage to either modality (i.e., visual or audio) can only be discovered through multi-modal models that can exploit both pieces of information simultaneously. Previous methods mainly adopt uni-modal video forensics and use supervised pre-training for forgery detection. This study proposes a new method based on a multi-modal self-supervised-learning (SSL) feature extractor to exploit inconsistency between audio and visual modalities for multi-modal video forgery detection. We use the transformer-based SSL pre-trained Audio-Visual HuBERT (AV-HuBERT) model as a visual and acoustic feature extractor and a multi-scale temporal convolutional neural network to capture the temporal correlation between the audio and visual modalities. Since AV-HuBERT only extracts visual features from the lip region, we also adopt another transformer-based video model to exploit facial features and capture spatial and temporal artifacts caused during the deepfake generation process. Experimental results show that our model outperforms all existing models and achieves new state-of-the-art performance on the FakeAVCeleb and DeepfakeTIMIT datasets.
Deepfake attacks, malicious manipulation of media containing people, are a serious concern for society. Conventional deepfake detection methods train supervised classifiers to distinguish real media from previously encountered deepfakes. Such techniques can only detect deepfakes similar to those previously seen, but not zero-day (previously unseen) attack types. As current deepfake generation techniques are changing at a breathtaking pace, new attack types are proposed frequently, making this a major issue. Our main observations are that: i) in many effective deepfake attacks, the fake media must be accompanied by false facts i.e. claims about the identity, speech, motion, or appearance of the person. For instance, when impersonating Obama, the attacker explicitly or implicitly claims that the fake media show Obama; ii) current generative techniques cannot perfectly synthesize the false facts claimed by the attacker. We therefore introduce the concept of "fact checking", adapted from fake news detection, for detecting zero-day deepfake attacks. Fact checking verifies that the claimed facts (e.g. identity is Obama), agree with the observed media (e.g. is the face really Obama's?), and thus can differentiate between real and fake media. Consequently, we introduce FACTOR, a practical recipe for deepfake fact checking and demonstrate its power in critical attack settings: face swapping and audio-visual synthesis. Although it is training-free, relies exclusively on off-the-shelf features, is very easy to implement, and does not see any deepfakes, it achieves better than state-of-the-art accuracy.
The ever-increasing use of synthetically generated content in different sectors of our everyday life, one for all media information, poses a strong need for deepfake detection tools in order to avoid the proliferation of altered messages. The process to identify manipulated content, in particular images and videos, is basically performed by looking for the presence of some inconsistencies and/or anomalies specifically due to the fake generation process. Different techniques exist in the scientific literature that exploit diverse ad-hoc features in order to highlight possible modifications. In this paper, we propose to investigate how deepfake creation can impact on the characteristics that the whole scene had at the time of the acquisition. In particular, when an image (video) is captured the overall geometry of the scene (e.g. surfaces) and the acquisition process (e.g. illumination) determine a univocal environment that is directly represented by the image pixel values; all these intrinsic relations are possibly changed by the deepfake generation process. By resorting to the analysis of the characteristics of the surfaces depicted in the image it is possible to obtain a descriptor usable to train a CNN for deepfake detection: we refer to such an approach as SurFake. Experimental results carried out on the FF++ dataset for different kinds of deepfake forgeries and diverse deep learning models confirm that such a feature can be adopted to discriminate between pristine and altered images; furthermore, experiments witness that it can also be combined with visual data to provide a certain improvement in terms of detection accuracy.
Vision Transformers (ViTs) have become ubiquitous in computer vision. Despite their success, ViTs lack inductive biases, which can make it difficult to train them with limited data. To address this challenge, prior studies suggest training ViTs with self-supervised learning (SSL) and fine-tuning sequentially. However, we observe that jointly optimizing ViTs for the primary task and a Self-Supervised Auxiliary Task (SSAT) is surprisingly beneficial when the amount of training data is limited. We explore the appropriate SSL tasks that can be optimized alongside the primary task, the training schemes for these tasks, and the data scale at which they can be most effective. Our findings reveal that SSAT is a powerful technique that enables ViTs to leverage the unique characteristics of both the self-supervised and primary tasks, achieving better performance than typical ViTs pre-training with SSL and fine-tuning sequentially. Our experiments, conducted on 10 datasets, demonstrate that SSAT significantly improves ViT performance while reducing carbon footprint. We also confirm the effectiveness of SSAT in the video domain for deepfake detection, showcasing its generalizability. Our code is available at https://github.com/dominickrei/Limited-data-vits.
Deep generative models can create remarkably photorealistic fake images while raising concerns about misinformation and copyright infringement, known as deepfake threats. Deepfake detection technique is developed to distinguish between real and fake images, where the existing methods typically learn classifiers in the image domain or various feature domains. However, the generalizability of deepfake detection against emerging and more advanced generative models remains challenging. In this paper, being inspired by the zero-shot advantages of Vision-Language Models (VLMs), we propose a novel approach called AntifakePrompt, using VLMs (e.g., InstructBLIP) and prompt tuning techniques to improve the deepfake detection accuracy over unseen data. We formulate deepfake detection as a visual question answering problem, and tune soft prompts for InstructBLIP to answer the real/fake information of a query image. We conduct full-spectrum experiments on datasets from a diversity of 3 held-in and 20 held-out generative models, covering modern text-to-image generation, image editing and adversarial image attacks. These testing datasets provide useful benchmarks in the realm of deepfake detection for further research. Moreover, results demonstrate that (1) the deepfake detection accuracy can be significantly and consistently improved (from 71.06% to 92.11%, in average accuracy over unseen domains) using pretrained vision-language models with prompt tuning; (2) our superior performance is at less cost of training data and trainable parameters, resulting in an effective and efficient solution for deepfake detection. Code and models can be found at https://github.com/nctu-eva-lab/AntifakePrompt.
In the dynamic realm of deepfake detection, this work presents an innovative approach to validate video content. The methodology blends advanced 2-dimensional and 3-dimensional Convolutional Neural Networks. The 3D model is uniquely tailored to capture spatiotemporal features via sliding filters, extending through both spatial and temporal dimensions. This configuration enables nuanced pattern recognition in pixel arrangement and temporal evolution across frames. Simultaneously, the 2D model leverages EfficientNet architecture, harnessing auto-scaling in Convolutional Neural Networks. Notably, this ensemble integrates Voting Ensembles and Adaptive Weighted Ensembling. Strategic prioritization of the 3-dimensional model's output capitalizes on its exceptional spatio-temporal feature extraction. Experimental validation underscores the effectiveness of this strategy, showcasing its potential in countering deepfake generation's deceptive practices.
Forged content shared widely on social media platforms is a major social problem that requires increased regulation and poses new challenges to the research community. The recent proliferation of hyper-realistic deepfake videos has drawn attention to the threat of audio and visual forgeries. Most previous work on detecting AI-generated fake videos only utilizes visual modality or audio modality. While there are some methods in the literature that exploit audio and visual modalities to detect forged videos, they have not been comprehensively evaluated on multi-modal datasets of deepfake videos involving acoustic and visual manipulations. Moreover, these existing methods are mostly based on CNN and suffer from low detection accuracy. Inspired by the recent success of Transformer in various fields, to address the challenges posed by deepfake technology, in this paper, we propose an Audio-Visual Transformer-based Ensemble Network (AVTENet) framework that considers both acoustic manipulation and visual manipulation to achieve effective video forgery detection. Specifically, the proposed model integrates several purely transformer-based variants that capture video, audio, and audio-visual salient cues to reach a consensus in prediction. For evaluation, we use the recently released benchmark multi-modal audio-video FakeAVCeleb dataset. For a detailed analysis, we evaluate AVTENet, its variants, and several existing methods on multiple test sets of the FakeAVCeleb dataset. Experimental results show that our best model outperforms all existing methods and achieves state-of-the-art performance on Testset-I and Testset-II of the FakeAVCeleb dataset.
Abstract— DeepFake detection aims to differentiate falsified faces from real ones. Most approaches formulate it as a binary classification problem by solely mining the local artifacts and inconsistencies of face forgery, which neglect the relation across local regions. Although several recent works explore local relation learning for DeepFake detection, they overlook the propagation of relational information and lead to limited performance gains. To address these issues, this paper provides a new perspective by formulating DeepFake detection as a graph classification problem, in which each facial region corresponds to a vertex. But relational information with large redundancy hinders the expressiveness of graphs. Inspired by the success of masked modeling, we propose Masked Relation Learning which decreases the redundancy to learn informative relational features. Specifically, a spatiotemporal attention module is exploited to learn the attention features of multiple facial regions. A relation learning module masks partial correlations between regions to reduce redundancy and then propagates the relational information across regions to capture the irregularity from a global view of the graph. We empirically discover that a moderate masking rate (e.g., 50%) brings the best performance gain. Experiments verify the effectiveness of Masked Relation Learning and demonstrate that our approach outperforms the state of the art by 2% AUC on the cross-dataset DeepFake video detection. Code will be available at https://github.com/zimyang/MaskRelation. Index Terms— Multimedia forensics, DeepFake detection, masked learning, relation feature.
A new algorithm for the detection of deepfakes in digital videos is presented. The I-frames were extracted in order to provide faster computation and analysis than approaches described in the literature. To identify the discriminating regions within individual video frames, the entire frame, background, face, eyes, nose, mouth, and face frame were analyzed separately. From the Discrete Cosine Transform (DCT), the Beta components were extracted from the AC coefficients and used as input to standard classifiers. Experimental results show that the eye and mouth regions are those most discriminative and able to determine the nature of the video under analysis.
Facial forgery by deepfakes has caused major security risks and raised severe societal concerns. As a countermeasure, a number of deepfake detection methods have been proposed. Most of them model deepfake detection as a binary classification problem using a backbone convolutional neural network (CNN) architecture pretrained for the task. These CNN-based methods have demonstrated very high efficacy in deepfake detection with the Area under the Curve (AUC) as high as $0.99$. However, the performance of these methods degrades significantly when evaluated across datasets and deepfake manipulation techniques. This draws our attention towards learning more subtle, local, and discriminative features for deepfake detection. In this paper, we formulate deepfake detection as a fine-grained classification problem and propose a new fine-grained solution to it. Specifically, our method is based on learning subtle and generalizable features by effectively suppressing background noise and learning discriminative features at various scales for deepfake detection. Through extensive experimental validation, we demonstrate the superiority of our method over the published research in cross-dataset and cross-manipulation generalization of deepfake detectors for the majority of the experimental scenarios.
Deepfakes are AI-generated media in which an image or video has been digitally modified. The advancements made in deepfake technology have led to privacy and security issues. Most deepfake detection techniques rely on the detection of a single modality. Existing methods for audio-visual detection do not always surpass that of the analysis based on single modalities. Therefore, this paper proposes an audio-visual-based method for deepfake detection, which integrates fine-grained deepfake identification with binary classification. We categorize the samples into four types by combining labels specific to each single modality. This method enhances the detection under intra-domain and cross-domain testing.
Deepfakes are synthetic media generated using deep generative algorithms and have posed a severe societal and political threat. Apart from facial manipulation and synthetic voice, recently, a novel kind of deepfakes has emerged with either audio or visual modalities manipulated. In this regard, a new generation of multimodal audio-visual deepfake detectors is being investigated to collectively focus on audio and visual data for multimodal manipulation detection. Existing multimodal (audio-visual) deepfake detectors are often based on the fusion of the audio and visual streams from the video. Existing studies suggest that these multimodal detectors often obtain equivalent performances with unimodal audio and visual deepfake detectors. We conjecture that the heterogeneous nature of the audio and visual signals creates distributional modality gaps and poses a significant challenge to effective fusion and efficient performance. In this paper, we tackle the problem at the representation level to aid the fusion of audio and visual streams for multimodal deepfake detection. Specifically, we propose the joint use of modality (audio and visual) invariant and specific representations. This ensures that the common patterns and patterns specific to each modality representing pristine or fake content are preserved and fused for multimodal deepfake manipulation detection. Our experimental results on FakeAVCeleb and KoDF audio-visual deepfake datasets suggest the enhanced accuracy of our proposed method over SOTA unimodal and multimodal audio-visual deepfake detectors by $17.8$% and $18.4$%, respectively. Thus, obtaining state-of-the-art performance.
In this paper, we challenge the conventional belief that supervised ImageNet-trained models have strong generalizability and are suitable for use as feature extractors in deepfake detection. We present a new measurement, "model separability," for visually and quantitatively assessing a model's raw capacity to separate data in an unsupervised manner. We also present a systematic benchmark for determining the correlation between deepfake detection and other computer vision tasks using pre-trained models. Our analysis shows that pre-trained face recognition models are more closely related to deepfake detection than other models. Additionally, models trained using self-supervised methods are more effective in separation than those trained using supervised methods. After fine-tuning all models on a small deepfake dataset, we found that self-supervised models deliver the best results, but there is a risk of overfitting. Our results provide valuable insights that should help researchers and practitioners develop more effective deepfake detection models.
Deepfake technology poses a significant threat to security and social trust. Although existing detection methods have shown high performance in identifying forgeries within datasets that use the same deepfake techniques for both training and testing, they suffer from sharp performance degradation when faced with cross-dataset scenarios where unseen deepfake techniques are tested. To address this challenge, we propose a Deep Information Decomposition (DID) framework to enhance the performance of Cross-dataset Deepfake Detection (CrossDF). Unlike most existing deepfake detection methods, our framework prioritizes high-level semantic features over specific visual artifacts. Specifically, it adaptively decomposes facial features into deepfake-related and irrelevant information, only using the intrinsic deepfake-related information for real/fake discrimination. Moreover, it optimizes these two kinds of information to be independent with a de-correlation learning module, thereby enhancing the model's robustness against various irrelevant information changes and generalization ability to unseen forgery methods. Our extensive experimental evaluation and comparison with existing state-of-the-art detection methods validate the effectiveness and superiority of the DID framework on cross-dataset deepfake detection.
Since photorealistic faces can be readily generated by facial manipulation technologies nowadays, potential malicious abuse of these technologies has drawn great concerns. Numerous deepfake detection methods are thus proposed. However, existing methods only focus on detecting one-step facial manipulation. As the emergence of easy-accessible facial editing applications, people can easily manipulate facial components using multi-step operations in a sequential manner. This new threat requires us to detect a sequence of facial manipulations, which is vital for both detecting deepfake media and recovering original faces afterwards. Motivated by this observation, we emphasize the need and propose a novel research problem called Detecting Sequential DeepFake Manipulation (Seq-DeepFake). Unlike the existing deepfake detection task only demanding a binary label prediction, detecting Seq-DeepFake manipulation requires correctly predicting a sequential vector of facial manipulation operations. To support a large-scale investigation, we construct the first Seq-DeepFake dataset, where face images are manipulated sequentially with corresponding annotations of sequential facial manipulation vectors. Based on this new dataset, we cast detecting Seq-DeepFake manipulation as a specific image-to-sequence task and propose a concise yet effective Seq-DeepFake Transformer (SeqFakeFormer). To better reflect real-world deepfake data distributions, we further apply various perturbations on the original Seq-DeepFake dataset and construct the more challenging Sequential DeepFake dataset with perturbations (Seq-DeepFake-P). To exploit deeper correlation between images and sequences when facing Seq-DeepFake-P, a dedicated Seq-DeepFake Transformer with Image-Sequence Reasoning (SeqFakeFormer++) is devised, which builds stronger correspondence between image-sequence pairs for more robust Seq-DeepFake detection.
Misinformation has become a pressing issue. Fake media, in both visual and textual forms, is widespread on the web. While various deepfake detection and text fake news detection methods have been proposed, they are only designed for single-modality forgery based on binary classification, let alone analyzing and reasoning subtle forgery traces across different modalities. In this paper, we highlight a new research problem for multi-modal fake media, namely Detecting and Grounding Multi-Modal Media Manipulation (DGM^4). DGM^4 aims to not only detect the authenticity of multi-modal media, but also ground the manipulated content, which requires deeper reasoning of multi-modal media manipulation. To support a large-scale investigation, we construct the first DGM^4 dataset, where image-text pairs are manipulated by various approaches, with rich annotation of diverse manipulations. Moreover, we propose a novel HierArchical Multi-modal Manipulation rEasoning tRansformer (HAMMER) to fully capture the fine-grained interaction between different modalities. HAMMER performs 1) manipulation-aware contrastive learning between two uni-modal encoders as shallow manipulation reasoning, and 2) modality-aware cross-attention by multi-modal aggregator as deep manipulation reasoning. Dedicated manipulation detection and grounding heads are integrated from shallow to deep levels based on the interacted multi-modal information. To exploit more fine-grained contrastive learning for cross-modal semantic alignment, we further integrate Manipulation-Aware Contrastive Loss with Local View and construct a more advanced model HAMMER++. Finally, we build an extensive benchmark and set up rigorous evaluation metrics for this new research problem. Comprehensive experiments demonstrate the superiority of HAMMER and HAMMER++.
Deepfake has taken the world by storm, triggering a trust crisis. Current deepfake detection methods are typically inadequate in generalizability, with a tendency to overfit to image contents such as the background, which are frequently occurring but relatively unimportant in the training dataset. Furthermore, current methods heavily rely on a few dominant forgery regions and may ignore other equally important regions, leading to inadequate uncovering of forgery cues. In this paper, we strive to address these shortcomings from three aspects: (1) We propose an innovative two-stream network that effectively enlarges the potential regions from which the model extracts forgery evidence. (2) We devise three functional modules to handle the multi-stream and multi-scale features in a collaborative learning scheme. (3) Confronted with the challenge of obtaining forgery annotations, we propose a Semi-supervised Patch Similarity Learning strategy to estimate patch-level forged location annotations. Empirically, our method demonstrates significantly improved robustness and generalizability, outperforming previous methods on six benchmarks, and improving the frame-level AUC on Deepfake Detection Challenge preview dataset from 0.797 to 0.835 and video-level AUC on CelebDF$\_$v1 dataset from 0.811 to 0.847. Our implementation is available at https://github.com/sccsok/Locate-and-Verify.