Deepfake Detection Research Articles

Detecting and Grounding Multi-Modal Media Manipulation and Beyond.

Misinformation has become a pressing issue. Fake media, in both visual and textual forms, is widespread on the web. While various DeepFake detection and text fake news detection methods have been proposed, they are only designed for single-modality forgery based on binary classification, let alone analyzing and reasoning subtle forgery traces across different modalities. In this paper, we highlight a new research problem for multi-modal fake media, namely Detecting and Grounding Multi-Modal Media Manipulation (DGM 4). DGM 4 aims to not only detect the authenticity of multi-modal media, but also ground the manipulated content (i.e., image bounding boxes and text tokens), which requires deeper reasoning of multi-modal media manipulation. To support a large-scale investigation, we construct the first DGM 4 dataset, where image-text pairs are manipulated by various approaches, with rich annotation of diverse manipulations. Moreover, we propose a novel HierArchical Multi-modal Manipulation rEasoning tRansformer (HAMMER) to fully capture the fine-grained interaction between different modalities. HAMMER performs: 1) manipulation-aware contrastive learning between two uni-modal encoders as shallow manipulation reasoning and 2) modality-aware cross-attention by multi-modal aggregator as deep manipulation reasoning. Dedicated manipulation detection and grounding heads are integrated from shallow to deep levels based on the interacted multi-modal information. To exploit more fine-grained contrastive learning for cross-modal semantic alignment, we further integrate Manipulation-Aware Contrastive Loss with Local View and construct a more advanced model HAMMER++. Finally, we build an extensive benchmark and set up rigorous evaluation metrics for this new research problem. Comprehensive experiments demonstrate the superiority of HAMMER and HAMMER++; several valuable observations are also revealed to facilitate future research in multi-modal media manipulation.

PVASS-MDD: Predictive Visual-Audio Alignment Self-Supervision for Multimodal Deepfake Detection

PVASS-MDD: Predictive Visual-Audio Alignment Self-Supervision for Multimodal Deepfake Detection

Deep Learning Approach to Detect Fake Video on Raspberry PI

Abstract: This project proposes a deep learning-based approach for real-time detection of fake videos on a resource-constrained device, specifically the Raspberry Pi. The solution combines the power of computer vision and recurrent neural networks to discern manipulated content from authentic videos effectively. The methodology involves using a pre-trained ResNeXt model for feature extraction, capturing spatial information from each video frame. These features are then fed into a Long Short-Term Memory (LSTM) network, allowing the model to understand and exploit temporal dependencies within the sequence of frames. The LSTM network learns patterns and nuances indicative of authentic or manipulated video content. The training process involves a carefully curated dataset containing both real and fake videos. The model is fine-tuned to optimize its performance, and metrics such as accuracy, precision, recall, and F1 score are employed for evaluation. To accommodate the constraints of the Raspberry Pi, the model is further optimized through techniques such as quantization, ensuring a balance between model size and inference accuracy. The final model is deployed on the Raspberry Pi, with a user-friendly interface capturing video frames in real-time. The system provides instantaneous feedback, indicating whether the observed video content is genuine or manipulated. This project contributes to the growing field of deepfake detection while addressing the challenges of implementing sophisticated models on edge devices. The combination of ResNeXt and LSTM offers a robust solution for discerning manipulated videos, making it suitable for real-world applications where computational resources are limited.

Real-Time Deepfake Video Detection Using Eye Movement Analysis with a Hybrid Deep Learning Approach

Deepfake technology uses artificial intelligence to create realistic but false audio, images, and videos. Deepfake technology poses a significant threat to the authenticity of visual content, particularly in live-stream scenarios where the immediacy of detection is crucial. Existing Deepfake detection approaches have limitations and challenges, prompting the need for more robust and accurate solutions. This research proposes an innovative approach: combining eye movement analysis with a hybrid deep learning model to address the need for real-time Deepfake detection. The proposed hybrid deep learning model integrates two deep neural network architectures, MesoNet4 and ResNet101, to leverage their respective architectures’ strengths for effective Deepfake classification. MesoNet4 is a lightweight CNN model designed explicitly to detect subtle manipulations in facial images. At the same time, ResNet101 handles complex visual data and robust feature extraction. Combining the localized feature learning of MesoNet4 with the deeper, more comprehensive feature representations of ResNet101, our robust hybrid model achieves enhanced performance in distinguishing between manipulated and authentic videos, which cannot be conducted with the naked eye or traditional methods. The model is evaluated on diverse datasets, including FaceForensics++, CelebV1, and CelebV2, demonstrating compelling accuracy results, with the hybrid model attaining an accuracy of 0.9873 on FaceForensics++, 0.9689 on CelebV1, and 0.9790 on CelebV2, showcasing its robustness and potential for real-world deployment in content integrity verification and video forensics applications.

A New Deepfake Detection Method Based on Compound Scaling Dual-Stream Attention Network

A New Deepfake Detection Method Based on Compound Scaling Dual-Stream Attention Network

Deep fake detection using an optimal deep learning model with multi head attention-based feature extraction scheme

Deep fake detection using an optimal deep learning model with multi head attention-based feature extraction scheme

Multi-domain awareness for compressed deepfake videos detection over social networks guided by common mechanisms between artifacts

The viral spread of massive deepfake videos over social networks has caused serious security problems. Despite the remarkable advancements achieved by existing deepfake detection algorithms, deepfake videos over social networks are inevitably influenced by compression factors. This causes deepfake detection performance to be limited by the following challenging issues: (a) interfering with compression artifacts, (b) loss of feature information, and (c) aliasing of feature distributions. In this paper, we analyze the common mechanism between compression artifacts and deepfake artifacts, revealing the structural similarity between them and providing a reliable theoretical basis for enhancing the robustness of deepfake detection models against compression. Firstly, based on the common mechanism between artifacts, we design a frequency domain adaptive notch filter to eliminate the interference of compression artifacts on specific frequency bands. Secondly, to reduce the sensitivity of deepfake detection models to unknown noise, we propose a spatial residual denoising strategy. Thirdly, to exploit the intrinsic correlation between feature vectors in the frequency domain branch and the spatial domain branch, we enhance deepfake features using an attention-based feature fusion method. Finally, we adopt a multi-task decision approach to enhance the discriminative power of the latent space representation of deepfakes, achieving deepfake detection with robustness against compression. Extensive experiments show that compared with the baseline methods, the detection performance of the proposed algorithm on compressed deepfake videos has been significantly improved. In particular, our model is resistant to various types of noise disturbances and can be easily combined with baseline detection models to improve their robustness.

Learning Self-distilled Features for Facial Deepfake Detection Using Visual Foundation Models: General Results and Demographic Analysis

Modern deepfake techniques produce highly realistic false media content with the potential for spreading harmful information, including fake news and incitements to violence. Deepfake detection methods aim to identify and counteract such content by employing machine learning algorithms, focusing mainly on detecting the presence of manipulation using spatial and temporal features. These methods often utilize Foundation Models trained on extensive unlabeled data through self-supervised approaches. This work extends previous research on deepfake detection, focusing on the effectiveness of these models while also considering biases, particularly concerning age, gender, and ethnicity, for ethical analysis. Experiments with DINOv2, a novel Vision Transformer-based Foundation Model, trained using the diverse Deepfake Detection Challenge Dataset, which encompasses several lighting conditions, resolutions, and demographic attributes, demonstrated improved deepfake detection when combined with a CNN classifier, with minimal bias towards these demographic characteristics.

A place for (socio)linguistics in audio deepfake detection and discernment: Opportunities for convergence and interdisciplinary collaboration

AbstractDeepfakes, particularly audio deepfakes, have become pervasive and pose unique, ever‐changing threats to society. This paper reviews the current research landscape on audio deepfakes. We assert that limitations of existing approaches to deepfake detection and discernment are areas where (socio)linguists can directly contribute to helping address the societal challenge of audio deepfakes. In particular, incorporating expert knowledge and developing techniques that everyday listeners can use to avoid deception are promising pathways for (socio)linguistics. Further opportunities exist for developing benevolent applications of this technology through generative AI methods as well.

Optimizing CNN-based Deepfake detection with firefly algorithm: A Hybrid Approach

Optimizing CNN-based Deepfake detection with firefly algorithm: A Hybrid Approach

Predicting manipulated regions in deepfake videos using convolutional vision transformers

Deepfake technology, which uses artificial intelligence to create and manipulate realistic synthetic media, poses a serious threat to the trustworthiness and integrity of digital content. Deepfakes can be used to generate, swap, or modify faces in videos, altering the appearance, identity, or expression of individuals. This study presents an approach for deepfake detection, based on a convolutional vision transformer (CViT), a hybrid model that combines convolutional neural networks (CNNs) and vision transformers (ViTs). The proposed study uses a 20-layer CNN to extract learnable features from face images, and a ViT to classify them into real or fake categories. The study also employs MTCNN, a multi-task cascaded network, to detect and align faces in videos, improving the accuracy and efficiency of the face extraction process. The method is assessed using the FaceForensics++ dataset, which comprises 15,800 images sourced from 1600 videos. With an 80:10:10 split ratio, the experimental results show that the proposed method achieves an accuracy of 92.5% and an AUC of 0.91. We use Gradient-Weighted Class Activation Mapping (Grad-CAM) visualization that highlights distinctive image regions used for making a decision. The proposed method demonstrates a high capability of detecting and distinguishing between genuine and manipulated videos, contributing to the enhancement of media authenticity and security.

Face Warping Deepfake Detection and Localization in a Digital Video using Transfer Learning Approach

Generative AI (GenAI) can generate high-resolution and complex content mimicking the creativity of humans, thereby benefiting industries such as gaming, entertainment, and product design. In recent times, AI-generated fake videos, commonly referred to as deepfakes, have become more commonplace and convincing. An additional deepfake technique, face warping, uses digital processing to noticeably distort shapes on a face. Tracking such warping in images and videos is crucial and preventing its use for destructive purposes. A technique is proposed for detecting and localizing face warped areas in video. The input video is extracted to perform various image pre-processing techniques that refine the video into a format that is more likely to classify the classes efficiently. Transfer learning is employed, and the pre-trained model is adopted to train using Convolutional Neural Network (CNN) with the source videos to identify face warping. Based on the experimental results, it was determined that the proposed model detects and localizes the warped areas of the face satisfactorily with an accuracy of 89.25%.

Multimodal Deepfake Detection

Abstract: Deepfake technology has become a significant threat to the integrity of multimedia content, posing challenges to areas such as cybersecurity, media forensics, and information authenticity. To address this, our research introduces a Multimodal Deepfake Detection system capable of identifying manipulated content by combining visual and auditory cues. The model employs convolutional neural networks (CNNs) to analyse video frames and process audio spectrograms, providing a comprehensive approach to detecting deepfake content. Experimental results demonstrate the system's effectiveness in accurately identifying both visual and auditory indicators of deepfake manipulation. This solution shows promise in combating the spread of deepfake content on digital platforms, thereby preserving the integrity and trustworthiness of multimedia content in the digital era

Deepfake Detection using Integrate-backward-integrate Logic Optimization Algorithm with CNN

The emergence of deepfake technology has spurred the need for robust and adaptive methods to detect manipulated media content. This study explores the integration of the Integrate-backward-integrate (IbI) Logic Optimization Algorithm with Convolutional Neural Networks (CNNs) for enhanced deepfake detection. The proposed approach involves a multi-phase iterative process: the CNN initially trained on a diverse dataset encompassing both real and deepfake images. The CNN serves as the foundation for the IbI-driven optimization. The integration phase employs the trained CNN to forward-integrate images, classifying them as real or deepfake. Subsequently, the IbI Logic Optimization Algorithm engages in the backward phase, utilizing feedback from the CNN's performance to iteratively refine the network's parameters, architecture, and feature extraction capabilities. This iterative optimization process aims to adaptively enhance the CNN's ability to discern subtle nuances between authentic and manipulated visuals. The re-integration phase evaluates the refined CNN's performance through multiple iterations, seeking to iteratively improve deepfake detection accuracy. Validation occurs using separate datasets to prevent overfitting and ensure the model's generalizability. The proposed method aims to enhance the CNN's adaptability to evolving deepfake techniques, addressing the dynamic nature of manipulative media creation. This fusion of IbI Logic Optimization with CNNs presents a promising avenue for bolstering deepfake detection capabilities. However, the effectiveness of this approach relies on dataset quality, network architecture, and the dynamic nature of deepfake generation techniques. Continuous refinement and validation are essential to adapt the model to new challenges posed by advancing deepfake technologies.

Feature fusion Vision Transformers using MLP-Mixer for enhanced deepfake detection

Deepfake technology, utilizing deep learning and computer vision, presents significant security threats by generating highly realistic synthetic media, such as images and videos. In this paper, we propose a feature fusion-based method for deepfake detection, harnessing the capabilities of three Vision Transformer (ViT) architectures: Dual Attention Vision Transformers (DaViT), Inception Transformer (iFormer), and Group Propagation Vision Transformer (GPViT). The proposed feature fusion method integrates the local–global contextual understanding of DaViT, the frequency spectrum broadening of iFormer, and the high-resolution feature retention of GPViT to provide a comprehensive analysis of visual data, crucial for detecting subtle manipulations typical in deepfakes. An MLP-Mixer (Multi-Layer Perceptron-Mixer) model is proposed for the feature fusion process for effective feature integration, enhancing the detection capabilities while preserving the individual strengths of each ViT model. The performance of the proposed method is evaluated using standard datasets, namely FaceForensics++ and Celeb-DF, demonstrating its robustness and generalizability across various scenarios. For the four manipulation techniques in the FaceForensics++ dataset, namely DeepFakes (DF), Face2Face (F2F), FaceSwap (FS), and NeuralTextures (NT), the proposed method achieves area under the curve (AUC) of 99.75%, 97.04%, 98.78%, and 87.49% respectively, Moreover, it demonstrates an AUC of 99.84% on the Celeb-DF dataset. The performance of the proposed model has been evaluated against many state-of-the-art methods to ensure its robustness and generalization capabilities.

AI Integrity Solutions for Deepfake Identification and Prevention

The increasing complexity of deepfake technology has sparked significant worries over individual privacy, the spread of false information, and deficiencies in cybersecurity. Deepfakes have the ability to effectively modify audio and visual content, resulting in a growing challenge to differentiate between real and fake content. To address this critical challenge, the study is conducting a survey to reveal a broad range of perspectives on the familiarity, encounters, and concerns related to deepfake technology. In addition, the study evaluates the effectiveness of current strategies in addressing the spread of deepfake material and proposes future approaches for improving the integrity of AI. The survey was delivered digitally, and responses were examined to provide an in- depth analysis of the latest techniques and difficulties in the context of deepfake detection. The outcomes demonstrate a range of perspectives on understanding deepfakes with an explicit agreement on the importance of risk presented by harmful deepfake applications. Although the participants showed an understanding of the available interventions, they also identified considerable challenges and the need for improved awareness, robust detection tools, and ethical standards in AI development to address the challenges posed by deepfakes with the present detection method. Implementing AI ethical guidelines to avoid deepfakes has a significant and beneficial effect on several industries by providing protection against their harmful effects. By fostering AI ethical guidelines, these policies are able to foster societal trust, mitigate risk, and cultivate a more robust digital environment.

An Approach to Deepfake Video Detection Based on ACO-PSO Features and Deep Learning

The rapid advancement of deepfake technology presents significant challenges in detecting highly convincing fake videos, posing risks such as misinformation, identity theft, and privacy violations. In response, this paper proposes an innovative approach to deepfake video detection by integrating features derived from ant colony optimization–particle swarm optimization (ACO-PSO) and deep learning techniques. The proposed methodology leverages ACO-PSO features and deep learning models to enhance detection accuracy and robustness. Features from ACO-PSO are extracted from the spatial and temporal characteristics of video frames, capturing subtle patterns indicative of deepfake manipulation. These features are then used to train a deep learning classifier to automatically distinguish between authentic and deepfake videos. Extensive experiments using comparative datasets demonstrate the superiority of the proposed method in terms of detection accuracy, robustness to manipulation techniques, and generalization to unseen data. The computational efficiency of the approach is also analyzed, highlighting its practical feasibility for real-time applications. The findings revealed that the proposed method achieved an accuracy of 98.91% and an F1 score of 99.12%, indicating remarkable success in deepfake detection. The integration of ACO-PSO features and deep learning enables comprehensive analysis, bolstering precision and resilience in detecting deepfake content. This approach addresses the challenges involved in facial forgery detection and contributes to safeguarding digital media integrity amid misinformation and manipulation.

JRC: Deepfake detection via joint reconstruction and classification

Deep learning has enabled realistic face manipulation for malicious purposes (e.g., deepfakes), which poses significant concerns over the integrity of the media in circulation. Most existing deep learning techniques for deepfake detection can achieve promising performance in the intra-dataset evaluation setting, but are unable to perform satisfactorily in the inter-dataset evaluation setting. Most previous methods use a backbone network to extract global features for making predictions and only employ binary supervision to train the network. Classification merely based on the learning of global features often leads to weak generalizability to deepfakes of unseen manipulation methods. In this paper, we design a two-branch Convolutional AutoEncoder (CAE), which considers the reconstruction and classification tasks simultaneously for deepfake detection. This Joint Reconstruction and Classification (JRC) method shares the information learned by one task with the other, each focusing on different aspects, and hence boosts the overall performance. JRC is end-to-end, and experiments demonstrate that it achieves state-of-the-art performance on three commonly-used datasets, particularly in the cross-dataset evaluation setting.

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.

Deepfake forensics: a survey of digital forensic methods for multimodal deepfake identification on social media

The rapid advancement of deepfake technology poses an escalating threat of misinformation and fraud enabled by manipulated media. Despite the risks, a comprehensive understanding of deepfake detection techniques has not materialized. This research tackles this knowledge gap by providing an up-to-date systematic survey of the digital forensic methods used to detect deepfakes. A rigorous methodology is followed, consolidating findings from recent publications on deepfake detection innovation. Prevalent datasets that underpin new techniques are analyzed. The effectiveness and limitations of established and emerging detection approaches across modalities including image, video, text and audio are evaluated. Insights into real-world performance are shared through case studies of high-profile deepfake incidents. Current research limitations around aspects like cross-modality detection are highlighted to inform future work. This timely survey furnishes researchers, practitioners and policymakers with a holistic overview of the state-of-the-art in deepfake detection. It concludes that continuous innovation is imperative to counter the rapidly evolving technological landscape enabling deepfakes.