Fake Images Research Articles

Fake Social Media Post Detection by Using Deep Learning Algorithm

In today's digital age, social media serves as both a boon and a bane, offering immense opportunities for personal growth while also being a breeding ground for misinformation and deception. The rise of sophisticated multimedia manipulation techniques has blurred the line between reality and fiction, presenting significant challenges to discerning genuine content from fabricated ones. This paper presents an overview of the escalating threat posed by fake posts on social media and proposes a novel approach for their detection. The proposed method leverages advanced technologies such as Error Level Analysis (ELA) and Convolutional Neural Networks (CNNs) to distinguish between authentic and manipulated posts. Unlike traditional approaches reliant on manual feature extraction, our framework employs deep learning methodologies for more nuanced pattern recognition and generalization to unseen data. By combining ELA for initial image analysis and CNNs for deep feature extraction, followed by classification using Support Vector Machines (SVMs) and K-Nearest Neighbors (KNNs), we achieve robust detection of fake images .Experimental results demonstrate the effectiveness of our approach, with a peak accuracy of 91.3% using Residual Networks and KNN. This method offers a promising solution to mitigate the proliferation of fake images on social media platforms, thereby combating the spread of misinformation, propaganda, and chaos.

Deepfake video detection: challenges and opportunities

Deepfake videos are a growing social issue. These videos are manipulated by artificial intelligence (AI) techniques (especially deep learning), an emerging societal issue. Malicious individuals misuse deepfake technologies to spread false information, such as fake images, videos, and audio. The development of convincing fake content threatens politics, security, and privacy. The majority of deepfake video detection methods are data-driven. This survey paper aims to thoroughly analyse deepfake video generation and detection. The paper’s main contribution is the classification of the many challenges encountered while detecting deepfake videos. The paper discusses data challenges such as unbalanced datasets and inadequate labelled training data. Training challenges include the need for many computational resources. It also addresses reliability challenges, including overconfidence in detection methods and emerging manipulation approaches. The research emphasises the dominance of deep learning-based methods in detecting deepfakes despite their computational efficiency and generalisation limitations. However, it also acknowledges the drawbacks of these approaches, such as their limited computing efficiency and generalisation. The research also critically evaluates deepfake datasets, emphasising the necessity for good-quality datasets to improve detection methods. The study also indicates major research gaps, guiding future deepfake detection research. This entails developing robust models for real-time detection.

DRD-GAN: A Novel Distributed Conditional Wasserstein Deep Convolutional Relativistic Discriminator GAN with Improved Convergence

Generative Adversarial Network (GAN) exhibited significant capabilities in many applications including image enhancement and manipulation, language translation, generating images/videos from text, creating art and music, and so on. However, train ing GANs using large datasets remains highly computationally intensive for most of the standalone systems. Additionally, standalone GANs often exhibit poor synchronization between their generator and discriminator with unstable training , poor convergence along with a large number of mode collapse s and vanishing / exploding gradients. Standalone GANs also failed to learn in a decentralized environment, where the data is distributed among several client machines. Some researchers have lately used the most prevalent decentralized setting available today, called Federated Learning (FL) to develop distributed -GAN strategies as the possible solutions, although their implementations mostly failed to address the above issues mainly because of: the training instability within the distributed component s, which eventually leads to the poor synchronization among the generator s and discriminator s scattered over several machines. In this work, we developed a computationally inexpensive Wasserstein conditional Distributed Relativistic Discriminator-GAN or DRD-GAN to alleviate the above issues. DRD-GAN stabilizes its train ing (with non-convex losses) by keeping a global generator in the central server and relativistic discriminator s in the local client s (one discriminator per client ), and uses Wasserstein-1 for computing local and global losses. It eventually avoids mode collapse s, vanishing/exploding gradient s (both in the presence of iid and non-iid samples) and helps DRD-GAN to produce high-quality fake images. Apart from that, the sheer unavailability of a capable conditional distributed -GAN model has become another motivation behind the current work. Essentially, we revisited the FL paradigms, locating one discriminator per client , and a generator in the central server that aggregates the updates coming from multiple discriminator s. Relativistic discriminator s in the client s are train ed on both iid and non-iid private data. We presented a detailed mathematical formulation of DRD-GAN and empirically evaluated our claims using CIFAR-10, MNIST, EuroSAT, and CelebA datasets.

Preserving manipulated and synthetic Deepfake detection through face texture naturalness

With the rapid development of deep learning and face recognition technology, AI(Artificial Intelligence) experts have rated Deepfake cheating as the top AI threat. It is difficult for the human eye to distinguish the fake face images generated by Deepfake. Therefore, it has become a popular tool for criminals to seek benefits. Deepfake can be mainly divided into two types, a manipulated Deepfake that falsifies images of others by targeting real faces, and a synthetic Deepfake using GAN to generate a new fake image. So far, seldom cybersecurity system is able to detect these two types simultaneously. In this article, we aim to propose a hybrid Deepfake detection mechanism (HDDM) based on face texture and naturalness degree. HDDM constructs a unique texture from a facial image based on CNN(Convolutional Neural Network) and builds a naturalness degree recognition model via DNN(Deep Neural Network) to help cheating detection. Experimental results have proved that HDDM possesses a sound effect and stability for synthetic and manipulated Deepfake attacks. In particular, the WildDeepfake simulation has demonstrated the possibility of applying HDDM to the real world.

Investigating the Evolving Landscape of Deepfake Technology: Generative AI's Role in it's Generation and Detection

The world of artificial intelligence is constantly changing, with Generative AI and Large Language Models (LLMs) leading the way in bringing new technological advancements. This paper offers a detailed look at these groundbreaking technologies and how they are shaping the digital world today. We explore the technical aspects of Generative AI and LLMs, explain their unique features, and compare them to traditional AI models.One of the key focuses of our research is the growing issue of DeepFakes—artificial intelligence-generated media that presents a significant challenge in verifying content. We conduct a thorough examination of few deepfake detection techniques out of which we will be implementing and analyzing one of them. Our research implements a framework for Deep Fake Image Detection. The suggested solution utilizes a RESNET-50(Residual Network with 50 layers) and MTCNN (Multi-task Cascaded Convolutional Networks) models for detecting whether the images are real or fake. This study conducts the Hypothesis testing for the proposed solution taking in consideration that the current Deepfake detection algorithms are less effective in detecting highly realistic Deepfakes compared to less sophisticated manipulations. By investigating the convergence of deep learning, neural networks, and sophisticated algorithms, we set the stage for advancements in AI-based content verification.

Parents and Children: Distinguishing Multimodal DeepFakes from Natural Images

Recent advancements in diffusion models have enabled the generation of realistic deepfakes from textual prompts in natural language. While these models have numerous benefits across various sectors, they have also raised concerns about the potential misuse of fake images and cast new pressures on fake image detection. In this work, we pioneer a systematic study on deepfake detection generated by state-of-the-art diffusion models. Firstly, we conduct a comprehensive analysis of the performance of contrastive and classification-based visual features, respectively extracted from CLIP-based models and ResNet or ViT-based architectures trained on image classification datasets. Our results demonstrate that fake images share common low-level cues, which render them easily recognizable. Further, we devise a multimodal setting wherein fake images are synthesized by different textual captions, which are used as seeds for a generator. Under this setting, we quantify the performance of fake detection strategies and introduce a contrastive-based disentangling method that lets us analyze the role of the semantics of textual descriptions and low-level perceptual cues. Finally, we release a new dataset, called COCOFake, containing about 1.2M images generated from the original COCO image-caption pairs using two recent text-to-image diffusion models, namely Stable Diffusion v1.4 and v2.0.

3D-DGGAN: A Data-Guided Generative Adversarial Network for High Fidelity in Medical Image Generation.

Three-dimensional images are frequently used in medical imaging research for classification, segmentation, and detection. However, the limited availability of 3D images hinders research progress due to network training difficulties. Generative methods have been proposed to create medical images using AI techniques. Nevertheless, 2D approaches have difficulty dealing with 3D anatomical structures, which can result in discontinuities between slices. To mitigate these discontinuities, several 3D generative networks have been proposed. However, the scarcity of available 3D images makes training these networks with limited samples inadequate for producing high-fidelity 3D images. We propose a data-guided generative adversarial network to provide high fidelity in 3D image generation. The generator creates fake images with noise using reference code obtained by extracting features from real images. The generator also creates decoded images using reference code without noise. These decoded images are compared to the real images to evaluate fidelity in the reference code. This generation process can create high-fidelity 3D images from only a small amount of real training data. Additionally, our method employs three types of discriminator: volume (evaluates all the slices), slab (evaluates a set of consecutive slices), and slice (evaluates randomly selected slices). The proposed discriminator enhances fidelity by differentiating between real and fake images based on detailed characteristics. Results from our method are compared with existing methods by using quantitative analysis such as Fréchet inception distance and maximum mean discrepancy. The results demonstrate that our method produces more realistic 3D images than existing methods.

FACE DETECTION SYSTEM USING CONVOLUTIONAL NEURAL NETWORKS: A REVIEW

Implementing a facial recognition system can help in identifying or verifying the identity of a person from a digital image. Accurate attendance records are critical to classroom assessment. However, manual attendance tracking can lead to errors, missed students, or duplicate records. The facial recognition attendance system includes facial recognition technology that recognizes and verifies an employee's facial features and automatically records attendance. The facial liveliness detection part is based on CNN, which creates a 3D model of the detected face to distinguish between real and fake images. The attendance system is written in Python and the user interface is designed using the WebView library. The main goal of facial recognition is to identify individuals, either individually or collectively. The number of positive faces may vary depending on the technology used for face recognition. Keywords: Face Recognition Attendance System, CNN Algorithm.

Wavelet Transform-based Methods for Forensic Analysis of Digital Images

In recent years, Generative Adversarial Networks (GANs) have been utilized in many applications of our daily lives to create digital media that was previously impossible. This paper utilizes GANs in multimedia forensics, where the precision and accuracy of image classification are crucial. The objective of the study is to detect sophisticated manipulated images generated by advanced deep learning methods using classical transformation methods. The method combines the classical wavelet transform for feature extraction with a classifier model to distinguish between real and fake images. The proposed method extracts unique features that differentiate between fake and real images, which are then fed to several gradient-boosting-based classifiers. The proposed method was tested using the FaceForensics++ dataset, which contains low-resolution video sequences of faces. The proposed model achieves an accuracy of 95% in detecting manipulated videos compared with 87% accuracy of other classical techniques.

Generalized and robust model for GAN-generated image detection

Generative adversarial network (GAN)-generated image detection is a crucial yet challenging problem. The advancement of diverse generative models makes it simpler to build realistic synthetic images, but it also increases the likelihood of using images maliciously. Recent techniques of fake image detection often overfit to specific GANs, incapable of generalizing to other GANs. Each GAN leaves its distinct fingerprint on the images it generates. We propose a simple and compact attention network that exploits high-frequency and noise residual patterns of images. We design two-channel image representations in the preprocessing phase, with one channel using a bilateral high pass filter (BiHPF) for high-frequency patterns and the other using photo response non-uniformity (PRNU) for noise residuals capturing from GAN-generated and real images. The feature maps pass through the attention network with a dense layer for classification tasks. We assess the generalizability and robustness of the model through extensive experiments. The model is evaluated on a benchmark dataset in various settings, including cross-category, cross-GAN models with varying class settings and different color manipulations. This study demonstrates that the proposed model outperforms state-of-the-art (SOTA) methods by approximately 5% in different experiment settings.

Score mismatching for generative modeling

We propose a new score-based model with one-step sampling. Previously, score-based models were burdened with heavy computations due to iterative sampling. For substituting the iterative process, we train a standalone generator to compress all the time steps with the gradient backpropagated from the score network. In order to produce meaningful gradients for the generator, the score network is trained to simultaneously match the real data distribution and mismatch the fake data distribution. This model has the following advantages: (1) For sampling, it generates a fake image with only one step forward. (2) For training, it only needs 10 diffusion steps. (3) Compared with consistency model, it is free of the ill-posed problem caused by consistency loss. On the popular CIFAR-10 dataset, our model outperforms Consistency Model and Denoising Score Matching, which demonstrates the potential of the framework. We further provide more examples on the MINIST and LSUN datasets. The code is available on GitHub.

Securing Social Media Imagery: GAN-Driven Encryption and CNN Analysis with DEA Protection

Generative adversarial networks (GANs) transform low-dimensional random noise into a photorealistic picture. The use of such misleading pictures laden with irrelevant information on social media platforms might lead to serious and challenging issues. The goal of this study is to create and identify the affected GAN pictures. Additionally, enhanced GAN detection accuracy by preprocessing and segmentation feature extraction. This study examines the effectiveness of several learning-based methods for detecting image-to-image translation. Generative adversarial networks use deep learning approaches like convolutional neural networks for generative modelling and the DEA (Data encryption standard) is used to produce the encryption key. To accurately identify fake images, an effective picture forgery detector is necessary. Recent advancements in generative adversarial networks (GANs) have been focused on producing photorealistic pictures quickly and successfully. However, GANs can complicate visual forensics and model attribution. Data from one source and pictures from another can have a wide range of uses, including in fields like computer vision, video, and language processing. The investigation of some photos reveals that both conventional and deep learning detectors may reach up to 95% detection accuracy. However, only deep learning maintains good accuracy on compressed data. An article that explains how to spot GAN-generated false images on social media also provides context on GANs and the theoretical concepts underlying them.

Robust GAN-Based CNN Model as Generative AI Application for Deepfake Detection

One of the most well-known generative AI models is the Generative Adversarial Network (GAN), which is frequently employed for data generation or augmentation. In this paper a reliable GAN-based CNN deepfake detection method utilizing GAN as an augmentation element is implemented. It aims to give the CNN model a big collection of images so that it can train better with the intrinsic qualities of the images. The major objective of this research is to show how GAN innovations have enhanced and increased the use of generative AI principles, particularly in fake image classification called Deepfakes that poses concerns about misrepresentation and individual privacy. For identifying these fake photos more synthetic images are created using the GAN model that closely resemble the training data. It has been observed that GAN-augmented datasets can improve the robustness and generality of CNN-based detection models, which correctly identify between real and false images by 96.35%.

Survey on Deep Fake Detection using Deep Learning

The rise of deep fake technology poses significant challenges to the authenticity and integrity of visual content on digital platforms. This paper presents the development of a web application aimed at detecting deep fake images and videos through the implementation of advanced deep learning models. Leveraging research in the field of deep fake detection, this application integrates state-of-the-art algorithm like CNNs for accurate classification tasks. Key features of the application include a user-friendly interface allowing for the upload and analysis of images and videos, leveraging the trained models to detect potential deep fakes. Additionally, the web application incorporates a sophisticated detection methods to enhance accuracy and reliability. The deployment of the web application on popular platforms aims to provide users with a tool to verify the authenticity of visual content, thereby mitigating the potential negative consequences of deep fake manipulation. Continuous monitoring, updates, and adaptation to emerging deep fake techniques are prioritized to ensure the web applications effectiveness and relevance in an ever-evolving landscape of digital content manipulation

CNN and RNN using Deepfake detection

Deep fake Detection is the task of detecting the fake images that have been generated using deep learning techniques. Deep fakes are created by using machine learning algorithms to manipulate or replace parts of an original video or image, such as the face of a person. The goal of deep fake detection is to identify such manipulations and distinguish them from real videos or images. Deep fake technology has emerged as a significant concern in recent years, presenting challenges in various fields, including media authenticity, privacy, and security.

Consistency label-activated region generating network for weakly supervised medical image segmentation

The current methods of auto-segmenting medical images are limited due to insufficient and ambiguous pathonmorphological labeling. In clinical practice, rough classification labels (such as disease or normal) are more commonly used than precise segmentation masks. However, there is still much to be explored regarding utilizing these weak clinical labels to accurately determine the lesion mask and guide medical image segmentation. In this paper, we proposed a weakly supervised medical image segmentation model to directly generate the lesion mask through a class activation map (CAM) guided cycle-consistency label-activated region transferring network. Cycle-consistency enforces that the mappings between the two domains should be reversible, which ensures that the original image can be reconstructed from the translated image. We developed a complementary branches fusion module to address the issue of blurry boundaries in CAM-guided segmentation. The complementary branch preserves the original semantic information of the non-lesion region and perfectly fuses the transferred feature of the lesion region with a complementary mask-constrained fake image generation process to clear the boundary of the lesion and non-lesion regions. This module allows the class transformation to focus solely on the label-activated region, resulting in more explicit segmentation. This model can accurately identify different region of medical images at the pixel-level while preserving the overall semantic structure semantion. It organizes disease labels and corresponding regions during image synthesis. Our method utilizes a joint discrimination strategy that significantly enhances the precision of the produced lesion mask. Extensive experiments of the proposed method on BraTs, ISIC and COVID-19 datasets demonstrate superior performance over existing state-of-the-art methods. The code and datasets are available at: https://github.com/mlcb-jlu/MedImgSeg.

Turning Waste into Wealth: Leveraging Low-Quality Samples for Enhancing Continuous Conditional Generative Adversarial Networks

Continuous Conditional Generative Adversarial Networks (CcGANs) enable generative modeling conditional on continuous scalar variables (termed regression labels). However, they can produce subpar fake images due to limited training data. Although Negative Data Augmentation (NDA) effectively enhances unconditional and class-conditional GANs by introducing anomalies into real training images, guiding the GANs away from low-quality outputs, its impact on CcGANs is limited, as it fails to replicate negative samples that may occur during the CcGAN sampling. We present a novel NDA approach called Dual-NDA specifically tailored for CcGANs to address this problem. Dual-NDA employs two types of negative samples: visually unrealistic images generated from a pre-trained CcGAN and label-inconsistent images created by manipulating real images' labels. Leveraging these negative samples, we introduce a novel discriminator objective alongside a modified CcGAN training algorithm. Empirical analysis on UTKFace and Steering Angle reveals that Dual-NDA consistently enhances the visual fidelity and label consistency of fake images generated by CcGANs, exhibiting a substantial performance gain over the vanilla NDA. Moreover, by applying Dual-NDA, CcGANs demonstrate a remarkable advancement beyond the capabilities of state-of-the-art conditional GANs and diffusion models, establishing a new pinnacle of performance. Our codes can be found at https://github.com/UBCDingXin/Dual-NDA.

Spectrum Translation for Refinement of Image Generation (STIG) Based on Contrastive Learning and Spectral Filter Profile

Currently, image generation and synthesis have remarkably progressed with generative models. Despite photo-realistic results, intrinsic discrepancies are still observed in the frequency domain. The spectral discrepancy appeared not only in generative adversarial networks but in diffusion models. In this study, we propose a framework to effectively mitigate the disparity in frequency domain of the generated images to improve generative performance of both GAN and diffusion models. This is realized by spectrum translation for the refinement of image generation (STIG) based on contrastive learning. We adopt theoretical logic of frequency components in various generative networks. The key idea, here, is to refine the spectrum of the generated image via the concept of image-to-image translation and contrastive learning in terms of digital signal processing. We evaluate our framework across eight fake image datasets and various cutting-edge models to demonstrate the effectiveness of STIG. Our framework outperforms other cutting-edges showing significant decreases in FID and log frequency distance of spectrum. We further emphasize that STIG improves image quality by decreasing the spectral anomaly. Additionally, validation results present that the frequency-based deepfake detector confuses more in the case where fake spectrums are manipulated by STIG.

TraceEvader: Making DeepFakes More Untraceable via Evading the Forgery Model Attribution

In recent few years, DeepFakes are posing serve threats and concerns to both individuals and celebrities, as realistic DeepFakes facilitate the spread of disinformation. Model attribution techniques aim at attributing the adopted forgery models of DeepFakes for provenance purposes and providing explainable results to DeepFake forensics. However, the existing model attribution techniques rely on the trace left in the DeepFake creation, which can become futile if such traces were disrupted. Motivated by our observation that certain traces served for model attribution appeared in both the high-frequency and low-frequency domains and play a divergent role in model attribution. In this work, for the first time, we propose a novel training-free evasion attack, TraceEvader, in the most practical non-box setting. Specifically, TraceEvader injects a universal imitated traces learned from wild DeepFakes into the high-frequency component and introduces adversarial blur into the domain of the low-frequency component, where the added distortion confuses the extraction of certain traces for model attribution. The comprehensive evaluation on 4 state-of-the-art (SOTA) model attribution techniques and fake images generated by 8 generative models including generative adversarial networks (GANs) and diffusion models (DMs) demonstrates the effectiveness of our method. Overall, our TraceEvader achieves the highest average attack success rate of 79% and is robust against image transformations and dedicated denoising techniques as well where the average attack success rate is still around 75%. Our TraceEvader confirms the limitations of current model attribution techniques and calls the attention of DeepFake researchers and practitioners for more robust-purpose model attribution techniques.

Deep Fake Image and Video Detection using Machine learning

Deep fake technology has rapidly advanced in recent years, presenting a significant challenge in distinguishing between authentic and manipulated media content. This abstract outlines the current state of research and development in deep fake image and video recognition, focusing on methodologies and advancements in detection techniques. The abstract begins by elucidating the motivation behind deep fake recognition, highlighting its implications in various domains such as politics, journalism, and entertainment. It then delves into the technical aspects, discussing the underlying principles of deep fake generation and the emergence of sophisticated algorithms capable of producing highly convincing fake media. Furthermore, the abstract provides insights into the evolving landscape of deep fake detection mechanisms. It discusses traditional approaches based on artifacts analysis and statistical methods, as well as the recent surge in machine learning and AI-based detection techniques. Notably, it emphasizes the importance of dataset curation, model training, and validation strategies in achieving robust detection performance Moreover, the abstract touches upon the challenges and limitations faced by current deep fake recognition systems, including the arms race between generators and detectors, scalability issues, and ethical considerations. It concludes by underscoring the significance of interdisciplinary collaboration and ongoing research efforts in addressing these challenges and fostering trust in digital media integrity. Overall, this abstract offers a concise overview of the landscape of deep fake image and video recognition, serving as a primer for researchers, practitioners, and policymakers engaged in combating the proliferation of synthetic media manipulation