Fake Face Research Articles

Boosting Deep Feature Fusion-based Detection Model for Fake Faces Generated by Generative Adversarial Networks for Consumer Space Environment

Boosting Deep Feature Fusion-based Detection Model for Fake Faces Generated by Generative Adversarial Networks for Consumer Space Environment

Face spoofing detection using Heterogeneous Auto-Similarities of Characteristics

Facial recognition systems are widely used in various daily applications due to their high accuracy rate and ease of use. Unfortunately, their performance drops drastically when encountering spoofing attacks. In this paper, a novel pipeline for face spoofing detection based on the extraction of Heterogeneous Auto-Similarities of Characteristics (HASC) descriptor from the HSV and YCbCr color spaces is proposed. To detect print and replay spoofing attacks, the HASC descriptor encodes linear and non-linear dependencies between low-level dense features of the color face image using covariance and information-theoretic measures. The combination of covariance and information-theoretic measures makes HASC an efficient descriptor to explore how the features are interrelated in real and fake faces. The HASC texture descriptions are extracted separately from each color channel of the HSV and YCbCr color spaces, and the resulting feature vectors are concatenated into an extended feature vector to better discriminate between real and fake faces. Extensive experiments are conducted on publicly available databases namely, Replay-Attack, CASIA FASD, and MSU MFSD. The obtained results demonstrate that while being of low dimension, the HASC descriptor when fed into a binary Support Vector Machine (SVM) classifier, achieves competitive results compared to the state-of-the-art.

A two-stage fake face image detection algorithm with expanded attention

A two-stage fake face image detection algorithm with expanded attention

Fake face detection based on a multi discriminator deep CNN architecture (MDD-CNN)

Due to the robustness of the deep learning tools used to design these applications, fakes are becoming increasingly common as these applications become more widely available and accessible to the general public. These fakes are typically fake faces or even fake people, which are difficult to distinguish from real individuals. Therefore, we need more efficient applications for fraud detection. In this work, we propose a new multi-discriminator architecture to distinguish fake faces from real ones. The architecture consists of three deep networks (discriminators) competing with each other, each trained differently. The final decision is made by voting based on the decisions of the three discriminators. The core element of our architecture is the proposed new adversarial deep network discriminator (NDGAN), which is trained in three different ways, resulting in three distinct discriminators. Discriminator 1 undergoes adversarial training, discriminator 2 is trained using transfer learning, and the third discriminator undergoes supervised training with a standard CNN using examples and counterexamples. Training and testing were performed on 70 000 real faces from the Flickr-Face-HQ (FFHQ) dataset, while 70 000 fake faces were generated using Nvidia’s StyleGAN. The tests conducted on the three networks produced significant results, with accuracy ranging from 79 % to 98 % for fake faces, and from 80 % to 98 % for real faces. The reliability of the discriminators contributes significantly to the overall performance of the multi-discriminator system, achieving an accuracy of 96 % for fake faces and 98 % for real faces.

The Assistance of Eye Blink Detection for Two- Factor Authentication

This paper discusses the implementation of a blink detection method using 68 facial markers and the eye aspect ratio (EAR) to provide strong protection for access systems. It investigates the importance of 68 facial markers and explores how to use eye landmarks to calculate the eye aspect ratio. Access systems, which should have good security measures and be difficult to decipher, are typically safeguarded by passwords or multi-factor verification, such as passwords combined with facial recognition. However, these methods have inherent weaknesses, including the risk of shoulder surfing with passwords and the potential to be deceived by fake face images with facial recognition. To address these issues, a two-factor authentication method by using password with eye blink recognition is proposed as an effective solution for access control. By incorporating real-time eye blinking action, the system can avoid the use of fake images and prevent shoulder spoofing. To demonstrate the practical application of eye blink detection for enhanced two-factor authentication, a web application called "Eblink" is introduced. Functional tests have been conducted to validate the application's core features.

Kapsül Ağları Kullanılarak Gerçek ve Sahte Yüz Verilerinin Sınıflandırılması

Recently, with the advancement of technology, artificial intelligence has begun to be used in many areas. It is used in many fields such as artificial intelligence, image processing, natural language processing, suggestion systems. The increase in the use of artificial intelligence has revealed the need for data. This situation has led to the production of new data from existing data. Today, generative adversarial networks (GAN) synthesize a wide variety of data inspired by existing data. These fake data produced from real image data can sometimes cause undesirable situations. It is an important issue to know whether the images, which are especially important for security, are fake or not. In this study, the classification of real human face data and fake face data generate from these data has been made. Fake face data were generated with the help of StyleGAN2-ADA from a small-sized dataset created by collecting facial data of a famous person. It is aimed to classify the generated fake face data and real face data with the capsule network model.

Fake Face Detection Based on Colour Textual Analysis Using Deep Convolutional Neural Network

Detecting fake faces has become a crucial endeavour within the realm of computer vision. The widespread availability of digital media has facilitated the creation and dissemination of deceptive and misleading content. A prominent strategy for identifying counterfeit faces employs advanced deep-learning methodologies that scrutinise both colour and textural attributes. This investigation is geared towards devising a method for discerning fake faces by leveraging the capabilities of convolutional neural networks (CNNs). These networks are trained to discriminate between authentic and forged images by discerning nuances in their colour characteristics. To achieve this, the MSU MFSD dataset will be harnessed, allowing for exploring colour textures and extracting facial traits across diverse colour channels, including RGB, HSV, and YCbCr.The proposed framework marks a notable stride in the realm of computer vision research, particularly given the prevalent employment of digital media, which has eased the generation and distribution of misleading or deceitful content. Developing dependable systems for identifying counterfeit faces holds immense potential in curtailing the proliferation of false information and upholding the integrity of digital media platforms.

Forged facial video detection framework based on multi-region temporal relationship feature

Face generation and manipulation techniques based on deep learning have enabled the creation of sophisticated forged facial videos, which are indistinguishable by human eyes. However, the illegal use of deep fake technology will have a serious impact on social stability, personal reputation, and even national security. Therefore, the detection technology of fake facial videos is of great significance to protect national security and maintain social order. Although the existing video-based fake face video detection technology has achieved good detection performance on the public fake face video database, there are still the following problems: (1) the existing technology uses a 2D attention mechanism to obtain local region features from face images and lacks a 3D attention mechanism to obtain local area features from face videos; (2) after obtaining local area features, the existing technology is directly used to classify or only model the inter-regional relationship of images without modeling the temporal relationship between regions of the video. This paper proposes a fake facial video detection framework based on multi-region temporal relationship features, including designing a three-dimensional attention mechanism to extract local features of multiple regions of the face from the video. In order to model the time series relationship between different face areas, a time series graph convolution neural network is also introduced to extract the time series relationship features between multiple areas. In order to model the time sequence relationship between different face regions, the convolution neural network of a time sequence diagram is also introduced to extract the characteristics of the time sequence relationship between multiple regions. Through the change characteristics of the time sequence relationship between face regions, the timing inconsistency of the face video is detected so as to determine whether the face has been deeply forged. Through experiments on multiple datasets, the experimental results of the model accuracy test show that the method proposed in the present invention achieves the highest detection accuracy, and the accuracy in the FaceForensics++ (low definition) dataset is 18.19% higher than that of the benchmark method. The experimental results of the generalization ability test show that the method proposed in the present invention achieves the highest generalization performance, and the detection accuracy in the Celeb-DF dataset is 11.92% higher than that of the benchmark method.

A novel forgery classification method based on multi‐scale feature capsule network in mobile edge computing

AbstractFace recognition is one of the most important applications of MEC. However, there have been many fake face data that can deceive MEC devices, causing serious problems such as information leakage. Face forgery detection can effectively solve this problem. Current face forgery detection methods have achieved high accuracy. However, most of the methods are researched on the classification of face authenticity. We find that studying multi‐classification of forgery methods can not only improve the accuracy of the model to identify fake faces, but also help improve the generalization ability of fake face classification. We argue that multi‐scale features and high‐frequency features can expose more detailed forgery artifacts. So, we design four modules, which take advantage of the complementarity of RGB features and frequency features, global features and local features. The first module is a residual‐guided multi‐scale spatial attention module, which uses residuals to guide the RGB feature extractor to extract fake features from a multi‐scale perspective. The second module is a multi‐scale retinal feature extraction module. The third module is a multi‐scale channel attention‐guided local frequency statistics module, which extracts local frequency responses using sliding‐window DCT. The last module is a capsule network classification module with overall correlation to classify the fused features. The information transfer between the subject capsule and the classification capsule can increase the integrity of the model, making the model converge faster. We conduct experiments on the databases FaceForensics++, DeepfakeDetection, and FakeAVCeleb. Experimental result shows that our method performs well on forgery classification.

Implementation of Generative Adversarial Network to Generate Fake Face Image

In recent years, many crimes use technology to generate someone's face which has a bad effect on that person. Generative adversarial network is a method to generate fake images using discriminators and generators. Conventional GAN involved binary cross entropy loss for discriminator training to classify original image from dataset and fake image that generated from generator. However, use of binary cross entropy loss cannot provided gradient information to generator in creating a good fake image. When generator creates a fake image, discriminator only gives a little feedback (gradient information) to generator update its model. It causes generator take a long time to update the model. To solve this problem, there is an LSGAN that used a loss function (least squared loss). Discriminator can provide astrong gradient signal to generator update the model even though image was far from decision boundary. In making fake images, researchers used Least Squares GAN (LSGAN) with discriminator-1 loss value is 0.0061, discriminator-2 loss value is 0.0036, and generator loss value is 0.575. With the small loss value of the three important components, discriminator accuracy value in terms of classification reaches 95% for original image and 99% for fake image. In classified original image and fake image in this studyusing a supervised contrastive loss classification model with an accuracy value of 99.93%.

People Taking Photos That Faces Never Share: Privacy Protection and Fairness Enhancement from Camera to User

The soaring number of personal mobile devices and public cameras poses a threat to fundamental human rights and ethical principles. For example, the stolen of private information such as face image by malicious third parties will lead to catastrophic consequences. By manipulating appearance of face in the image, most of existing protection algorithms are effective but irreversible. Here, we propose a practical and systematic solution to invertiblely protect face information in the full-process pipeline from camera to final users. Specifically, We design a novel lightweight Flow-based Face Encryption Method (FFEM) on the local embedded system privately connected to the camera, minimizing the risk of eavesdropping during data transmission. FFEM uses a flow-based face encoder to encode each face to a Gaussian distribution and encrypts the encoded face feature by random rotating the Gaussian distribution with the rotation matrix is as the password. While encrypted latent-variable face images are sent to users through public but less reliable channels, password will be protected through more secure channels through technologies such as asymmetric encryption, blockchain, or other sophisticated security schemes. User could select to decode an image with fake faces from the encrypted image on the public channel. Only trusted users are able to recover the original face using the encrypted matrix transmitted in secure channel. More interestingly, by tuning Gaussian ball in latent space, we could control the fairness of the replaced face on attributes such as gender and race. Extensive experiments demonstrate that our solution could protect privacy and enhance fairness with minimal effect on high-level downstream task.

Enhancing Face Spoofing Attack Detection: Performance Evaluation of a VGG-19 CNN Model

With the wide use of facial verification and authentication systems, the performance evaluation of Spoofing Attack Detection (SAD) module in the systems is important, because poor performance leads to successful face spoofing attacks. Previous studies on face SAD used a pretrained Visual Geometry Group (VGG) -16 architecture to extract feature maps from face images using the convolutional layers, and trained a face SAD model to classify real and fake face images, obtaining poor performance for unseen face images. Therefore, this study aimed to evaluate the performance of VGG-19 face SAD model. Experimental approach was used to build the model. VGG-19 algorithm was used to extract Red Green Blue (RGB) and deep neural network features from the face datasets. Evaluation results showed that the performance of the VGG-19 face SAD model improved by 6% compared with the state-of-the-art approaches, with the lowest equal error rate (EER) of 0.4%. In addition, the model had strong generalization ability in top-1 accuracy, threshold operation, quality test, fake face test, equal error rate, and overall test standard evaluation metrics.

Hierarchical supervisions with two-stream network for Deepfake detection

Recently, the quality of face generation and manipulation has reached impressive levels, making it difficult even for humans to distinguish real and fake faces. At the same time, methods to distinguish fake faces from reals came out, such as Deepfake detection. However, the task of Deepfake detection remains challenging, especially the low-quality fake images circulating on the Internet and the diversity of face generation methods. In this work, we propose a new Deepfake detection network that could effectively distinguish both high-quality and low-quality faces generated by various generation methods. First, we design a two-stream framework that incorporates a regular spatial stream and a frequency stream to handle the low-quality problem since we find that the frequency domain artifacts of low-quality images will be preserved. Second, we introduce hierarchical supervisions in a coarse-to-fine manner, which consists of a coarse binary classification branch to classify reals and fakes and a five-category classification branch to classify reals and four different types of fakes. Extensive experiments have proved the effectiveness of our framework on several widely used datasets.

TVN: Detect Deepfakes Images using Texture Variation Network

Face manipulation technology is rapidly developing, making it impossible for human eyes to recognize fake face photos. Convolutional Neural Network (CNN) discriminators, on the other hand, can fast achieve high accuracy in distinguishing fake/real face photos. In this paper, we look at how CNN models discern between fake and real faces. Face forgery detection relies heavily on Texture Variation Network (TVN) information, according to our findings. We propose a new model, TVN, for robust face fraud detection, based on Convolution and pyramid pooling (PP), as a result of the aforesaid discovery. To produce a stationary representation of composition difference information, Convolution combines pixel intensity and pixel gradient information. Simultaneously, multi-scale information fusion based on the PP can prevent the texture features from being destroyed. Our TVN beats previous techniques on numerous databases, including Faceforensics++, DeeperForensics-1.0, Celeb-DF, and DFDC. The TVN is more resistant to image distortion, such as JPEG compression and blur, which is critical in the wild.

Using Content and Trace Feature Extractors for Exposing Fake Faces through Deep Learning

Using Content and Trace Feature Extractors for Exposing Fake Faces through Deep Learning

VIOLA jones algorithm with capsule graph network for deepfake detection.

DeepFake is a forged image or video created using deep learning techniques. The present fake content of the detection technique can detect trivial images such as barefaced fake faces. Moreover, the capability of current methods to detect fake faces is minimal. Many recent types of research have made the fake detection algorithm from rule-based to machine-learning models. However, the emergence of deep learning technology with intelligent improvement motivates this specified research to use deep learning techniques. Thus, it is proposed to have VIOLA Jones's (VJ) algorithm for selecting the best features with Capsule Graph Neural Network (CN). The graph neural network is improved by capsule-based node feature extraction to improve the results of the graph neural network. The experiment is evaluated with CelebDF-FaceForencics++ (c23) datasets, which combines FaceForencies++ (c23) and Celeb-DF. In the end, it is proved that the accuracy of the proposed model has achieved 94.

A presentation attack detection network based on dynamic convolution and multi-level feature fusion with security and reliability

In the Internet of Things environment, most facial recognition systems are highly susceptible to face spoofing attacks. To increase the security and reliability of such systems, this paper proposes an anti-spoofing method for facial recognition systems based on optical flow and texture features. The spoofing-detection algorithm first generates the optical flow field map of the face area using the optical flow method and a face-detection method, based on two consecutive frames of the captured face video. Then, the original RGB face area image and optical flow field map are input into a two-channel convolutional neural network to extract and fuse the features of the face. Finally, based on the optical flow and texture features, this method classifies real and fake faces. In addition, to better generate the optical flow field map containing liveness information, a motion amplification algorithm is applied to enhance the 0.04–0.4 Hz signal in the video frame by 20 times. For texture and optical flow presentation, we propose a lightweight network with dynamic convolution and multi-level feature fusion blocks. This paper used the Replay Attack spoofing dataset from IDIAP, consisting of 1300 videos, for model training, verification, and testing. Experiments showed that the algorithm proposed in the paper performed well on the Replay Attack data set and achieved a half total error rate of 0.66%.

Text-to-image generation based on AttnDM-GAN and DMAttn-GAN: applications and challenges

The deep fake faces generation using generative adversarial networks (GANs) has reached an incredible level of realism where people can’t differentiate the real from the fake. Text-to-face is a very challenging task compared to other text-to-image syntheses because of the detailed, precise, and complex nature of the human faces in addition to the textual description details. Providing an accurate realistic text-to-image model can be useful for many applications such as criminal identification where the model will be acting as the forensic artist. This paper presents text-to-image generation based on attention dynamic memory (AttnDM-GAN) and dynamic memory attention (DMAttn-GAN) that are applied to different datasets with an analysis that shows the different complexity of different datasets’ categories, the quality of the datasets, and their effect on the results of the resolution and consistency of the generated images.

Deep learning approaches for robust deep fake detection

Detecting deepfake images using a deep learning approach, particularly using model Densenet121, involves training a neural network to differentiate between authentic and manipulated images. Deepfakes have gained prominence due to advances in deep learning, especially generative adversarial networks (GANs). They pose significant challenges to the veracity of digital content, as they can be used to create realistic and deceptive media. Deepfakes are realistic looking fake media generated by many artificial intelligence tools like face2face and deepfake, which pose a severe threat to public. As more deepfakes are spreading, we really need better ways to find and prevent them. Deepfake involves creation of highly realistic images and videos and misuse them for spreading fake news, defaming individuals, and possess a significant threat to the integrity of digital content. Our project “Deep Learning Approaches for Robust Deep Fake Detection” aims to address this critical issue by developing a robust system for identification and localization of deep fake content by using ‘Densenet121’ model. This proposed framework seamlessly integrates forgery detection and localization. The dataset used in this project is “140k Real and Fake Faces”, and it consists of 70k real faces from Flickr dataset collected by Nvidia and 70k fake faces sampled from the 1 million Fake faces generated by StyleGAN. For localization purpose, we use GRAD-CAM method to accurately identify the morphed regions. Overall, our goal is to make deepfake detection more effective and reliable in today’s digital landscape.

A facial geometry based detection model for face manipulation using CNN-LSTM architecture

This issue of DeepFake technique that may cause great threat to privacy, democracy, and national security has attracted the attention of deep learning researchers. DeepFake detection, therefore, has been a very hot issue in deep learning research. The face landmark feature maps are often used by many DeepFake approaches in generating fake faces. It also provides key information to help to detect manipulated face images. In this paper, we propose a detection approach for manipulated face images. To make full use of face landmark information, we propose a facial geometry prior module (FGPM) to extract facial geometry feature maps. Then the facial geometry feature maps are embedded into upsampling feature maps generated by the CNN-LSTM network. The proposed FGPM exploits facial maps and frequency domain correlation to analyze the discriminative characteristics between manipulated and non-manipulated regions by incorporating the CNN-LSTM network. Finally, a decoder is used to learn the mapping from low-resolution feature maps to pixel-wise to predict manipulation localization. Or a softmax classifier is used to predict real or fake face images. By experimenting on several popular datasets, the proposed detection model has demonstrated the capability of localizing manipulation at the pixel level and with a high prediction on real or fake face images.