Detecting diffusion-generated deepfake images remains an open problem. Current detection methods fail against an adversary who adds imperceptible adversarial perturbations to the deepfake to evade detection. In this work, we propose Disjoint Diffusion Deepfake Detection (D4), a deepfake detector designed to improve black-box adversarial robustness beyond de facto solutions such as adversarial training. D4 uses an ensemble of models over disjoint subsets of the frequency spectrum to significantly improve adversarial robustness. Our key insight is to leverage a redundancy in the frequency domain and apply a saliency partitioning technique to disjointly distribute frequency components across multiple models. We formally prove that these disjoint ensembles lead to a reduction in the dimensionality of the input subspace where adversarial deepfakes lie, thereby making adversarial deepfakes harder to find for black-box attacks. We then empirically validate the D4 method against several black-box attacks and find that D4 significantly outperforms existing state-of-the-art defenses applied to diffusion-generated deepfake detection. We also demonstrate that D4 provides robustness against adversarial deepfakes from unseen data distributions as well as unseen generative techniques.
Various deepfake detectors have been proposed, but challenges still exist to detect images of unknown categories or GAN models outside of the training settings. Such issues arise from the overfitting issue, which we discover from our own analysis and the previous studies to originate from the frequency-level artifacts in generated images. We find that ignoring the frequency-level artifacts can improve the detector's generalization across various GAN models, but it can reduce the model's performance for the trained GAN models. Thus, we design a framework to generalize the deepfake detector for both the known and unseen GAN models. Our framework generates the frequency-level perturbation maps to make the generated images indistinguishable from the real images. By updating the deepfake detector along with the training of the perturbation generator, our model is trained to detect the frequency-level artifacts at the initial iterations and consider the image-level irregularities at the last iterations. For experiments, we design new test scenarios varying from the training settings in GAN models, color manipulations, and object categories. Numerous experiments validate the state-of-the-art performance of our deepfake detector.
Deepfake detection methods based on convolutional neural networks (CNN) have demonstrated high accuracy. \textcolor{black}{However, these methods often suffer from decreased performance when faced with unknown forgery methods and common transformations such as resizing and blurring, resulting in deviations between training and testing domains.} This phenomenon, known as overfitting, poses a significant challenge. To address this issue, we propose a novel block shuffling regularization method. Firstly, our approach involves dividing the images into blocks and applying both intra-block and inter-block shuffling techniques. This process indirectly achieves weight-sharing across different dimensions. Secondly, we introduce an adversarial loss algorithm to mitigate the overfitting problem induced by the shuffling noise. Finally, we restore the spatial layout of the blocks to capture the semantic associations among them. Extensive experiments validate the effectiveness of our proposed method, which surpasses existing approaches in forgery face detection. Notably, our method exhibits excellent generalization capabilities, demonstrating robustness against cross-dataset evaluations and common image transformations. Especially our method can be easily integrated with various CNN models. Source code is available at \href{https://github.com/NoWindButRain/BlockShuffleLearning}{Github}.
One of the most pressing challenges for the detection of face-manipulated videos is generalising to forgery methods not seen during training while remaining effective under common corruptions such as compression. In this paper, we examine whether we can tackle this issue by harnessing videos of real talking faces, which contain rich information on natural facial appearance and behaviour and are readily available in large quantities online. Our method, termed RealForensics, consists of two stages. First, we exploit the natural correspondence between the visual and auditory modalities in real videos to learn, in a self-supervised cross-modal manner, temporally dense video representations that capture factors such as facial movements, expression, and identity. Second, we use these learned representations as targets to be predicted by our forgery detector along with the usual binary forgery classification task; this encourages it to base its real/fake decision on said factors. We show that our method achieves state-of-the-art performance on cross-manipulation generalisation and robustness experiments, and examine the factors that contribute to its performance. Our results suggest that leveraging natural and unlabelled videos is a promising direction for the development of more robust face forgery detectors.
Face manipulation methods can be misused to affect an individual's privacy or to spread disinformation. To this end, we introduce a novel data-driven approach that produces image-specific perturbations which are embedded in the original images. The key idea is that these protected images prevent face manipulation by causing the manipulation model to produce a predefined manipulation target (uniformly colored output image in our case) instead of the actual manipulation. In addition, we propose to leverage differentiable compression approximation, hence making generated perturbations robust to common image compression. In order to prevent against multiple manipulation methods simultaneously, we further propose a novel attention-based fusion of manipulation-specific perturbations. Compared to traditional adversarial attacks that optimize noise patterns for each image individually, our generalized model only needs a single forward pass, thus running orders of magnitude faster and allowing for easy integration in image processing stacks, even on resource-constrained devices like smartphones.
Despite significant advancements of deep learning-based forgery detectors for distinguishing manipulated deepfake images, most detection approaches suffer from moderate to significant performance degradation with low-quality compressed deepfake images. Because of the limited information in low-quality images, detecting low-quality deepfake remains an important challenge. In this work, we apply frequency domain learning and optimal transport theory in knowledge distillation (KD) to specifically improve the detection of low-quality compressed deepfake images. We explore transfer learning capability in KD to enable a student network to learn discriminative features from low-quality images effectively. In particular, we propose the Attention-based Deepfake detection Distiller (ADD), which consists of two novel distillations: 1) frequency attention distillation that effectively retrieves the removed high-frequency components in the student network, and 2) multi-view attention distillation that creates multiple attention vectors by slicing the teacher's and student's tensors under different views to transfer the teacher tensor's distribution to the student more efficiently. Our extensive experimental results demonstrate that our approach outperforms state-of-the-art baselines in detecting low-quality compressed deepfake images.
In recent years, visual forgery has reached a level of sophistication that humans cannot identify fraud, which poses a significant threat to information security. A wide range of malicious applications have emerged, such as fake news, defamation or blackmailing of celebrities, impersonation of politicians in political warfare, and the spreading of rumours to attract views. As a result, a rich body of visual forensic techniques has been proposed in an attempt to stop this dangerous trend. In this paper, we present a benchmark that provides in-depth insights into visual forgery and visual forensics, using a comprehensive and empirical approach. More specifically, we develop an independent framework that integrates state-of-the-arts counterfeit generators and detectors, and measure the performance of these techniques using various criteria. We also perform an exhaustive analysis of the benchmarking results, to determine the characteristics of the methods that serve as a comparative reference in this never-ending war between measures and countermeasures.
With the rapid development of generation model, AI-based face manipulation technology, which called DeepFakes, has become more and more realistic. This means of face forgery can attack any target, which poses a new threat to personal privacy and property security. Moreover, the misuse of synthetic video shows potential dangers in many areas, such as identity harassment, pornography and news rumors. Inspired by the fact that the spatial coherence and temporal consistency of physiological signal are destroyed in the generated content, we attempt to find inconsistent patterns that can distinguish between real videos and synthetic videos from the variations of facial pixels, which are highly related to physiological information. Our approach first applies Eulerian Video Magnification (EVM) at multiple Gaussian scales to the original video to enlarge the physiological variations caused by the change of facial blood volume, and then transform the original video and magnified videos into a Multi-Scale Eulerian Magnified Spatial-Temporal map (MEMSTmap), which can represent time-varying physiological enhancement sequences on different octaves. Then, these maps are reshaped into frame patches in column units and sent to the vision Transformer to learn the spatio-time descriptors of frame levels. Finally, we sort out the feature embedding and output the probability of judging whether the video is real or fake. We validate our method on the FaceForensics++ and DeepFake Detection datasets. The results show that our model achieves excellent performance in forgery detection, and also show outstanding generalization capability in cross-data domain.
Deepfakes are becoming increasingly popular in both good faith applications such as in entertainment and maliciously intended manipulations such as in image and video forgery. Primarily motivated by the latter, a large number of deepfake detectors have been proposed recently in order to identify such content. While the performance of such detectors still need further improvements, they are often assessed in simple if not trivial scenarios. In particular, the impact of benign processing operations such as transcoding, denoising, resizing and enhancement are not sufficiently studied. This paper proposes a more rigorous and systematic framework to assess the performance of deepfake detectors in more realistic situations. It quantitatively measures how and to which extent each benign processing approach impacts a state-of-the-art deepfake detection method. By illustrating it in a popular deepfake detector, our benchmark proposes a framework to assess robustness of detectors and provides valuable insights to design more efficient deepfake detectors.
Deep generative modeling has the potential to cause significant harm to society. Recognizing this threat, a magnitude of research into detecting so-called "Deepfakes" has emerged. This research most often focuses on the image domain, while studies exploring generated audio signals have, so-far, been neglected. In this paper we make three key contributions to narrow this gap. First, we provide researchers with an introduction to common signal processing techniques used for analyzing audio signals. Second, we present a novel data set, for which we collected nine sample sets from five different network architectures, spanning two languages. Finally, we supply practitioners with two baseline models, adopted from the signal processing community, to facilitate further research in this area.
Substantial progress in spoofing and deepfake detection has been made in recent years. Nonetheless, the community has yet to make notable inroads in providing an explanation for how a classifier produces its output. The dominance of black box spoofing detection solutions is at further odds with the drive toward trustworthy, explainable artificial intelligence. This paper describes our use of SHapley Additive exPlanations (SHAP) to gain new insights in spoofing detection. We demonstrate use of the tool in revealing unexpected classifier behaviour, the artefacts that contribute most to classifier outputs and differences in the behaviour of competing spoofing detection models. The tool is both efficient and flexible, being readily applicable to a host of different architecture models in addition to related, different applications. All results reported in the paper are reproducible using open-source software.
As the remarkable development of facial manipulation technologies is accompanied by severe security concerns, face forgery detection has become a recent research hotspot. Most existing detection methods train a binary classifier under global supervision to judge real or fake. However, advanced manipulations only perform small-scale tampering, posing challenges to comprehensively capture subtle and local forgery artifacts, especially in high compression settings and cross-dataset scenarios. To address such limitations, we propose a novel framework named Multi-modal Contrastive Classification by Locally Correlated Representations(MC-LCR), for effective face forgery detection. Instead of specific appearance features, our MC-LCR aims to amplify implicit local discrepancies between authentic and forged faces from both spatial and frequency domains. Specifically, we design the shallow style representation block that measures the pairwise correlation of shallow feature maps, which encodes local style information to extract more discriminative features in the spatial domain. Moreover, we make a key observation that subtle forgery artifacts can be further exposed in the patch-wise phase and amplitude spectrum and exhibit different clues. According to the complementarity of amplitude and phase information, we develop a patch-wise amplitude and phase dual attention module to capture locally correlated inconsistencies with each other in the frequency domain. Besides the above two modules, we further introduce the collaboration of supervised contrastive loss with cross-entropy loss. It helps the network learn more discriminative and generalized representations. Through extensive experiments and comprehensive studies, we achieve state-of-the-art performance and demonstrate the robustness and generalization of our method.
Significant advances in deep learning have obtained hallmark accuracy rates for various computer vision applications. However, advances in deep generative models have also led to the generation of very realistic fake content, also known as deepfakes, causing a threat to privacy, democracy, and national security. Most of the current deepfake detection methods are deemed as a binary classification problem in distinguishing authentic images or videos from fake ones using two-class convolutional neural networks (CNNs). These methods are based on detecting visual artifacts, temporal or color inconsistencies produced by deep generative models. However, these methods require a large amount of real and fake data for model training and their performance drops significantly in cross dataset evaluation with samples generated using advanced deepfake generation techniques. In this paper, we thoroughly evaluate the efficacy of deep face recognition in identifying deepfakes, using different loss functions and deepfake generation techniques. Experimental investigations on challenging Celeb-DF and FaceForensics++ deepfake datasets suggest the efficacy of deep face recognition in identifying deepfakes over two-class CNNs and the ocular modality. Reported results suggest a maximum Area Under Curve (AUC) of 0.98 and an Equal Error Rate (EER) of 7.1% in detecting deepfakes using face recognition on the Celeb-DF dataset. This EER is lower by 16.6% compared to the EER obtained for the two-class CNN and the ocular modality on the Celeb-DF dataset. Further on the FaceForensics++ dataset, an AUC of 0.99 and EER of 2.04% were obtained. The use of biometric facial recognition technology has the advantage of bypassing the need for a large amount of fake data for model training and obtaining better generalizability to evolving deepfake creation techniques.
Deep generative networks in recent years have reinforced the need for caution while consuming various modalities of digital information. One avenue of deepfake creation is aligned with injection and removal of tumors from medical scans. Failure to detect medical deepfakes can lead to large setbacks on hospital resources or even loss of life. This paper attempts to address the detection of such attacks with a structured case study. Specifically, we evaluate eight different machine learning algorithms, which including three conventional machine learning methods, support vector machine, random forest, decision tree, and five deep learning models, DenseNet121, DenseNet201, ResNet50, ResNet101, VGG19, on distinguishing between tampered and untampered images.For deep learning models, the five models are used for feature extraction, then fine-tune for each pre-trained model is performed. The findings of this work show near perfect accuracy in detecting instances of tumor injections and removals.
Manipulated videos, especially those where the identity of an individual has been modified using deep neural networks, are becoming an increasingly relevant threat in the modern day. In this paper, we seek to develop a generalizable, explainable solution to detecting these manipulated videos. To achieve this, we design a series of forgery detection systems that each focus on one individual part of the face. These parts-based detection systems, which can be combined and used together in a single architecture, meet all of our desired criteria - they generalize effectively between datasets and give us valuable insights into what the network is looking at when making its decision. We thus use these detectors to perform detailed empirical analysis on the FaceForensics++, Celeb-DF, and Facebook Deepfake Detection Challenge datasets, examining not just what the detectors find but also collecting and analyzing useful related statistics on the datasets themselves.
The rapid progress in the ease of creating and spreading ultra-realistic media over social platforms calls for an urgent need to develop a generalizable deepfake detection technique. It has been observed that current deepfake generation methods leave discriminative artifacts in the frequency spectrum of fake images and videos. Inspired by this observation, in this paper, we present a novel approach, termed as MD-CSDNetwork, for combining the features in the spatial and frequency domains to mine a shared discriminative representation for classifying \textit{deepfakes}. MD-CSDNetwork is a novel cross-stitched network with two parallel branches carrying the spatial and frequency information, respectively. We hypothesize that these multi-domain input data streams can be considered as related supervisory signals. The supervision from both branches ensures better performance and generalization. Further, the concept of cross-stitch connections is utilized where they are inserted between the two branches to learn an optimal combination of domain-specific and shared representations from other domains automatically. Extensive experiments are conducted on the popular benchmark dataset namely FaceForeniscs++ for forgery classification. We report improvements over all the manipulation types in FaceForensics++ dataset and comparable results with state-of-the-art methods for cross-database evaluation on the Celeb-DF dataset and the Deepfake Detection Dataset.
Existing deepfake-detection methods focus on passive detection, i.e., they detect fake face images via exploiting the artifacts produced during deepfake manipulation. A key limitation of passive detection is that it cannot detect fake faces that are generated by new deepfake generation methods. In this work, we propose FaceGuard, a proactive deepfake-detection framework. FaceGuard embeds a watermark into a real face image before it is published on social media. Given a face image that claims to be an individual (e.g., Nicolas Cage), FaceGuard extracts a watermark from it and predicts the face image to be fake if the extracted watermark does not match well with the individual's ground truth one. A key component of FaceGuard is a new deep-learning-based watermarking method, which is 1) robust to normal image post-processing such as JPEG compression, Gaussian blurring, cropping, and resizing, but 2) fragile to deepfake manipulation. Our evaluation on multiple datasets shows that FaceGuard can detect deepfakes accurately and outperforms existing methods.
Significant advancements made in the generation of deepfakes have caused security and privacy issues. Attackers can easily impersonate a person's identity in an image by replacing his face with the target person's face. Moreover, a new domain of cloning human voices using deep-learning technologies is also emerging. Now, an attacker can generate realistic cloned voices of humans using only a few seconds of audio of the target person. With the emerging threat of potential harm deepfakes can cause, researchers have proposed deepfake detection methods. However, they only focus on detecting a single modality, i.e., either video or audio. On the other hand, to develop a good deepfake detector that can cope with the recent advancements in deepfake generation, we need to have a detector that can detect deepfakes of multiple modalities, i.e., videos and audios. To build such a detector, we need a dataset that contains video and respective audio deepfakes. We were able to find a most recent deepfake dataset, Audio-Video Multimodal Deepfake Detection Dataset (FakeAVCeleb), that contains not only deepfake videos but synthesized fake audios as well. We used this multimodal deepfake dataset and performed detailed baseline experiments using state-of-the-art unimodal, ensemble-based, and multimodal detection methods to evaluate it. We conclude through detailed experimentation that unimodals, addressing only a single modality, video or audio, do not perform well compared to ensemble-based methods. Whereas purely multimodal-based baselines provide the worst performance.
The advancement in numerous generative models has a two-fold effect: a simple and easy generation of realistic synthesized images, but also an increased risk of malicious abuse of those images. Thus, it is important to develop a generalized detector for synthesized images of any GAN model or object category, including those unseen during the training phase. However, the conventional methods heavily depend on the training settings, which cause a dramatic decline in performance when tested with unknown domains. To resolve the issue and obtain a generalized detection ability, we propose Bilateral High-Pass Filters (BiHPF), which amplify the effect of the frequency-level artifacts that are known to be found in the synthesized images of generative models. Numerous experimental results validate that our method outperforms other state-of-the-art methods, even when tested with unseen domains.
Applications of deep learning to synthetic media generation allow the creation of convincing forgeries, called DeepFakes, with limited technical expertise. DeepFake detection is an increasingly active research area. In this paper, we analyze an existing DeepFake detection technique based on head pose estimation, which can be applied when fake images are generated with an autoencoder-based face swap. Existing literature suggests that this method is an effective DeepFake detector, and its motivating principles are attractively simple. With an eye towards using these principles to develop new DeepFake detectors, we conduct a reproducibility study of the existing method. We conclude that its merits are dramatically overstated, despite its celebrated status. By investigating this discrepancy we uncover a number of important and generalizable insights related to facial landmark detection, identity-agnostic head pose estimation, and algorithmic bias in DeepFake detectors. Our results correct the current literature's perception of state of the art performance for DeepFake detection.