Advancements in generative models, like Deepfake allows users to imitate a targeted person and manipulate online interactions. It has been recognized that disinformation may cause disturbance in society and ruin the foundation of trust. This article presents DeFakePro, a decentralized consensus mechanism-based Deepfake detection technique in online video conferencing tools. Leveraging Electrical Network Frequency (ENF), an environmental fingerprint embedded in digital media recording, affords a consensus mechanism design called Proof-of-ENF (PoENF) algorithm. The similarity in ENF signal fluctuations is utilized in the PoENF algorithm to authenticate the media broadcasted in conferencing tools. By utilizing the video conferencing setup with malicious participants to broadcast deep fake video recordings to other participants, the DeFakePro system verifies the authenticity of the incoming media in both audio and video channels.
Despite encouraging progress in deepfake detection, generalization to unseen forgery types remains a significant challenge due to the limited forgery clues explored during training. In contrast, we notice a common phenomenon in deepfake: fake video creation inevitably disrupts the statistical regularity in original videos. Inspired by this observation, we propose to boost the generalization of deepfake detection by distinguishing the "regularity disruption" that does not appear in real videos. Specifically, by carefully examining the spatial and temporal properties, we propose to disrupt a real video through a Pseudo-fake Generator and create a wide range of pseudo-fake videos for training. Such practice allows us to achieve deepfake detection without using fake videos and improves the generalization ability in a simple and efficient manner. To jointly capture the spatial and temporal disruptions, we propose a Spatio-Temporal Enhancement block to learn the regularity disruption across space and time on our self-created videos. Through comprehensive experiments, our method exhibits excellent performance on several datasets.
Facial forgery by deepfakes has raised severe societal concerns. Several solutions have been proposed by the vision community to effectively combat the misinformation on the internet via automated deepfake detection systems. Recent studies have demonstrated that facial analysis-based deep learning models can discriminate based on protected attributes. For the commercial adoption and massive roll-out of the deepfake detection technology, it is vital to evaluate and understand the fairness (the absence of any prejudice or favoritism) of deepfake detectors across demographic variations such as gender and race. As the performance differential of deepfake detectors between demographic subgroups would impact millions of people of the deprived sub-group. This paper aims to evaluate the fairness of the deepfake detectors across males and females. However, existing deepfake datasets are not annotated with demographic labels to facilitate fairness analysis. To this aim, we manually annotated existing popular deepfake datasets with gender labels and evaluated the performance differential of current deepfake detectors across gender. Our analysis on the gender-labeled version of the datasets suggests (a) current deepfake datasets have skewed distribution across gender, and (b) commonly adopted deepfake detectors obtain unequal performance across gender with mostly males outperforming females. Finally, we contributed a gender-balanced and annotated deepfake dataset, GBDF, to mitigate the performance differential and to promote research and development towards fairness-aware deep fake detectors. The GBDF dataset is publicly available at: https://github.com/aakash4305/GBDF
This paper aims to interpret how deepfake detection models learn artifact features of images when just supervised by binary labels. To this end, three hypotheses from the perspective of image matching are proposed as follows. 1. Deepfake detection models indicate real/fake images based on visual concepts that are neither source-relevant nor target-relevant, that is, considering such visual concepts as artifact-relevant. 2. Besides the supervision of binary labels, deepfake detection models implicitly learn artifact-relevant visual concepts through the FST-Matching (i.e. the matching fake, source, target images) in the training set. 3. Implicitly learned artifact visual concepts through the FST-Matching in the raw training set are vulnerable to video compression. In experiments, the above hypotheses are verified among various DNNs. Furthermore, based on this understanding, we propose the FST-Matching Deepfake Detection Model to boost the performance of forgery detection on compressed videos. Experiment results show that our method achieves great performance, especially on highly-compressed (e.g. c40) videos.
Deepfake face not only violates the privacy of personal identity, but also confuses the public and causes huge social harm. The current deepfake detection only stays at the level of distinguishing true and false, and cannot trace the original genuine face corresponding to the fake face, that is, it does not have the ability to trace the source of evidence. The deepfake countermeasure technology for judicial forensics urgently calls for deepfake traceability. This paper pioneers an interesting question about face deepfake, active forensics that "know it and how it happened". Given that deepfake faces do not completely discard the features of original faces, especially facial expressions and poses, we argue that original faces can be approximately speculated from their deepfake counterparts. Correspondingly, we design a disentangling reversing network that decouples latent space features of deepfake faces under the supervision of fake-original face pair samples to infer original faces in reverse.
Recent advances in face forgery techniques produce nearly visually untraceable deepfake videos, which could be leveraged with malicious intentions. As a result, researchers have been devoted to deepfake detection. Previous studies have identified the importance of local low-level cues and temporal information in pursuit to generalize well across deepfake methods, however, they still suffer from robustness problem against post-processings. In this work, we propose the Local- & Temporal-aware Transformer-based Deepfake Detection (LTTD) framework, which adopts a local-to-global learning protocol with a particular focus on the valuable temporal information within local sequences. Specifically, we propose a Local Sequence Transformer (LST), which models the temporal consistency on sequences of restricted spatial regions, where low-level information is hierarchically enhanced with shallow layers of learned 3D filters. Based on the local temporal embeddings, we then achieve the final classification in a global contrastive way. Extensive experiments on popular datasets validate that our approach effectively spots local forgery cues and achieves state-of-the-art performance.
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 (e.g. image captioning) task and propose a concise yet effective Seq-DeepFake Transformer (SeqFakeFormer). Moreover, we build a comprehensive benchmark and set up rigorous evaluation protocols and metrics for this new research problem. Extensive experiments demonstrate the effectiveness of SeqFakeFormer. Several valuable observations are also revealed to facilitate future research in broader deepfake detection problems.
Machine learning models are often brittle on production data despite achieving high accuracy on benchmark datasets. Benchmark datasets have traditionally served dual purposes: first, benchmarks offer a standard on which machine learning researchers can compare different methods, and second, benchmarks provide a model, albeit imperfect, of the real world. The incompleteness of test benchmarks (and the data upon which models are trained) hinder robustness in machine learning, enable shortcut learning, and leave models systematically prone to err on out-of-distribution and adversarially perturbed data. The mismatch between a single static benchmark dataset and a production dataset has traditionally been described as a dataset shift. In an effort to clarify how to address the mismatch between test benchmarks and production data, we introduce context shift to describe semantically meaningful changes in the underlying data generation process. Moreover, we identify three methods for addressing context shift that would otherwise lead to model prediction errors: first, we describe how human intuition and expert knowledge can identify semantically meaningful features upon which models systematically fail, second, we detail how dynamic benchmarking - with its focus on capturing the data generation process - can promote generalizability through corroboration, and third, we highlight that clarifying a model's limitations can reduce unexpected errors. Robust machine learning is focused on model performance beyond benchmarks, and as such, we consider three model organism domains - facial expression recognition, deepfake detection, and medical diagnosis - to highlight how implicit assumptions in benchmark tasks lead to errors in practice. By paying close attention to the role of context, researchers can design more comprehensive benchmarks, reduce context shift errors, and increase generalizability.
Audio DeepFakes allow the creation of high-quality, convincing utterances and therefore pose a threat due to its potential applications such as impersonation or fake news. Methods for detecting these manipulations should be characterized by good generalization and stability leading to robustness against attacks conducted with techniques that are not explicitly included in the training. In this work, we introduce Attack Agnostic Dataset - a combination of two audio DeepFakes and one anti-spoofing datasets that, thanks to the disjoint use of attacks, can lead to better generalization of detection methods. We present a thorough analysis of current DeepFake detection methods and consider different audio features (front-ends). In addition, we propose a model based on LCNN with LFCC and mel-spectrogram front-end, which not only is characterized by a good generalization and stability results but also shows improvement over LFCC-based mode - we decrease standard deviation on all folds and EER in two folds by up to 5%.
Deepfake Generation Techniques are evolving at a rapid pace, making it possible to create realistic manipulated images and videos and endangering the serenity of modern society. The continual emergence of new and varied techniques brings with it a further problem to be faced, namely the ability of deepfake detection models to update themselves promptly in order to be able to identify manipulations carried out using even the most recent methods. This is an extremely complex problem to solve, as training a model requires large amounts of data, which are difficult to obtain if the deepfake generation method is too recent. Moreover, continuously retraining a network would be unfeasible. In this paper, we ask ourselves if, among the various deep learning techniques, there is one that is able to generalise the concept of deepfake to such an extent that it does not remain tied to one or more specific deepfake generation methods used in the training set. We compared a Vision Transformer with an EfficientNetV2 on a cross-forgery context based on the ForgeryNet dataset. From our experiments, It emerges that EfficientNetV2 has a greater tendency to specialize often obtaining better results on training methods while Vision Transformers exhibit a superior generalization ability that makes them more competent even on images generated with new methodologies.
The step function is one of the simplest and most natural activation functions for deep neural networks (DNNs). As it counts 1 for positive variables and 0 for others, its intrinsic characteristics (e.g., discontinuity and no viable information of subgradients) impede its development for several decades. Even if there is an impressive body of work on designing DNNs with continuous activation functions that can be deemed as surrogates of the step function, it is still in the possession of some advantageous properties, such as complete robustness to outliers and being capable of attaining the best learning-theoretic guarantee of predictive accuracy. Hence, in this paper, we aim to train DNNs with the step function used as an activation function (dubbed as 0/1 DNNs). We first reformulate 0/1 DNNs as an unconstrained optimization problem and then solve it by a block coordinate descend (BCD) method. Moreover, we acquire closed-form solutions for sub-problems of BCD as well as its convergence properties. Furthermore, we also integrate $\ell_{2,0}$-regularization into 0/1 DNN to accelerate the training process and compress the network scale. As a result, the proposed algorithm has a high performance on classifying MNIST and Fashion-MNIST datasets. As a result, the proposed algorithm has a desirable performance on classifying MNIST, FashionMNIST, Cifar10, and Cifar100 datasets.
Recent advances in deep learning have enabled realistic digital alterations to videos, known as deepfakes. This technology raises important societal concerns regarding disinformation and authenticity, galvanizing the development of numerous deepfake detection algorithms. At the same time, there are significant differences between training data and in-the-wild video data, which may undermine their practical efficacy. We simulate data corruption techniques and examine the performance of a state-of-the-art deepfake detection algorithm on corrupted variants of the FaceForensics++ dataset. While deepfake detection models are robust against video corruptions that align with training-time augmentations, we find that they remain vulnerable to video corruptions that simulate decreases in video quality. Indeed, in the controversial case of the video of Gabonese President Bongo's new year address, the algorithm, which confidently authenticates the original video, judges highly corrupted variants of the video to be fake. Our work opens up both technical and ethical avenues of exploration into practical deepfake detection in global contexts.
Deepfakes pose a serious threat to digital well-being by fueling misinformation. As deepfakes get harder to recognize with the naked eye, human users become increasingly reliant on deepfake detection models to decide if a video is real or fake. Currently, models yield a prediction for a video's authenticity, but do not integrate a method for alerting a human user. We introduce a framework for amplifying artifacts in deepfake videos to make them more detectable by people. We propose a novel, semi-supervised Artifact Attention module, which is trained on human responses to create attention maps that highlight video artifacts. These maps make two contributions. First, they improve the performance of our deepfake detection classifier. Second, they allow us to generate novel "Deepfake Caricatures": transformations of the deepfake that exacerbate artifacts to improve human detection. In a user study, we demonstrate that Caricatures greatly increase human detection, across video presentation times and user engagement levels. Overall, we demonstrate the success of a human-centered approach to designing deepfake mitigation methods.
Most of previous deepfake detection researches bent their efforts to describe and discriminate artifacts in human perceptible ways, which leave a bias in the learned networks of ignoring some critical invariance features intra-class and underperforming the robustness of internet interference. Essentially, the target of deepfake detection problem is to represent natural faces and fake faces at the representation space discriminatively, and it reminds us whether we could optimize the feature extraction procedure at the representation space through constraining intra-class consistence and inter-class inconsistence to bring the intra-class representations close and push the inter-class representations apart? Therefore, inspired by contrastive representation learning, we tackle the deepfake detection problem through learning the invariant representations of both classes and propose a novel real-centric consistency learning method. We constraint the representation from both the sample level and the feature level. At the sample level, we take the procedure of deepfake synthesis into consideration and propose a novel forgery semantical-based pairing strategy to mine latent generation-related features. At the feature level, based on the centers of natural faces at the representation space, we design a hard positive mining and synthesizing method to simulate the potential marginal features. Besides, a hard negative fusion method is designed to improve the discrimination of negative marginal features with the help of supervised contrastive margin loss we developed. The effectiveness and robustness of the proposed method has been demonstrated through extensive experiments.
Deepfakes are a form of synthetic image generation used to generate fake videos of individuals for malicious purposes. The resulting videos may be used to spread misinformation, reduce trust in media, or as a form of blackmail. These threats necessitate automated methods of deepfake video detection. This paper investigates whether temporal information can improve the deepfake detection performance of deep learning models. To investigate this, we propose a framework that classifies new and existing approaches by their defining characteristics. These are the types of feature extraction: automatic or manual, and the temporal relationship between frames: dependent or independent. We apply this framework to investigate the effect of temporal dependency on a model's deepfake detection performance. We find that temporal dependency produces a statistically significant (p < 0.05) increase in performance in classifying real images for the model using automatic feature selection, demonstrating that spatio-temporal information can increase the performance of deepfake video detection models.
There have been emerging a number of benchmarks and techniques for the detection of deepfakes. However, very few works study the detection of incrementally appearing deepfakes in the real-world scenarios. To simulate the wild scenes, this paper suggests a continual deepfake detection benchmark (CDDB) over a new collection of deepfakes from both known and unknown generative models. The suggested CDDB designs multiple evaluations on the detection over easy, hard, and long sequence of deepfake tasks, with a set of appropriate measures. In addition, we exploit multiple approaches to adapt multiclass incremental learning methods, commonly used in the continual visual recognition, to the continual deepfake detection problem. We evaluate existing methods, including their adapted ones, on the proposed CDDB. Within the proposed benchmark, we explore some commonly known essentials of standard continual learning. Our study provides new insights on these essentials in the context of continual deepfake detection. The suggested CDDB is clearly more challenging than the existing benchmarks, which thus offers a suitable evaluation avenue to the future research. Both data and code are available at https://github.com/Coral79/CDDB.
Residual-domain feature is very useful for Deepfake detection because it suppresses irrelevant content features and preserves key manipulation traces. However, inappropriate residual prediction will bring side effects on detection accuracy. In addition, residual-domain features are easily affected by image operations such as compression. Most existing works exploit either spatial-domain features or residual-domain features, while neglecting that two types of features are mutually correlated. In this paper, we propose a guided residuals network, namely GRnet, which fuses spatial-domain and residual-domain features in a mutually reinforcing way, to expose face images generated by Deepfake. Different from existing prediction based residual extraction methods, we propose a manipulation trace extractor (MTE) to directly remove the content features and preserve manipulation traces. MTE is a fine-grained method that can avoid the potential bias caused by inappropriate prediction. Moreover, an attention fusion mechanism (AFM) is designed to selectively emphasize feature channel maps and adaptively allocate the weights for two streams. The experimental results show that the proposed GRnet achieves better performances than the state-of-the-art works on four public fake face datasets including HFF, FaceForensics++, DFDC and Celeb-DF. Especially, GRnet achieves an average accuracy of 97.72% on the HFF dataset, which is at least 5.25% higher than the existing works.
Enabled by recent improvements in generation methodologies, DeepFakes have become mainstream due to their increasingly better visual quality, the increase in easy-to-use generation tools and the rapid dissemination through social media. This fact poses a severe threat to our societies with the potential to erode social cohesion and influence our democracies. To mitigate the threat, numerous DeepFake detection schemes have been introduced in the literature but very few provide a web service that can be used in the wild. In this paper, we introduce the MeVer DeepFake detection service, a web service detecting deep learning manipulations in images and video. We present the design and implementation of the proposed processing pipeline that involves a model ensemble scheme, and we endow the service with a model card for transparency. Experimental results show that our service performs robustly on the three benchmark datasets while being vulnerable to Adversarial Attacks. Finally, we outline our experience and lessons learned when deploying a research system into production in the hopes that it will be useful to other academic and industry teams.
Deepfakes utilise Artificial Intelligence (AI) techniques to create synthetic media where the likeness of one person is replaced with another. There are growing concerns that deepfakes can be maliciously used to create misleading and harmful digital contents. As deepfakes become more common, there is a dire need for deepfake detection technology to help spot deepfake media. Present deepfake detection models are able to achieve outstanding accuracy (>90%). However, most of them are limited to within-dataset scenario, where the same dataset is used for training and testing. Most models do not generalise well enough in cross-dataset scenario, where models are tested on unseen datasets from another source. Furthermore, state-of-the-art deepfake detection models rely on neural network-based classification models that are known to be vulnerable to adversarial attacks. Motivated by the need for a robust deepfake detection model, this study adapts metamorphic testing (MT) principles to help identify potential factors that could influence the robustness of the examined model, while overcoming the test oracle problem in this domain. Metamorphic testing is specifically chosen as the testing technique as it fits our demand to address learning-based system testing with probabilistic outcomes from largely black-box components, based on potentially large input domains. We performed our evaluations on MesoInception-4 and TwoStreamNet models, which are the state-of-the-art deepfake detection models. This study identified makeup application as an adversarial attack that could fool deepfake detectors. Our experimental results demonstrate that both the MesoInception-4 and TwoStreamNet models degrade in their performance by up to 30\% when the input data is perturbed with makeup.
In this paper, we present novel synthetic training data called self-blended images (SBIs) to detect deepfakes. SBIs are generated by blending pseudo source and target images from single pristine images, reproducing common forgery artifacts (e.g., blending boundaries and statistical inconsistencies between source and target images). The key idea behind SBIs is that more general and hardly recognizable fake samples encourage classifiers to learn generic and robust representations without overfitting to manipulation-specific artifacts. We compare our approach with state-of-the-art methods on FF++, CDF, DFD, DFDC, DFDCP, and FFIW datasets by following the standard cross-dataset and cross-manipulation protocols. Extensive experiments show that our method improves the model generalization to unknown manipulations and scenes. In particular, on DFDC and DFDCP where existing methods suffer from the domain gap between the training and test sets, our approach outperforms the baseline by 4.90% and 11.78% points in the cross-dataset evaluation, respectively.