Academic literature on the topic 'FaceForensics++'
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the lists of relevant articles, books, theses, conference reports, and other scholarly sources on the topic 'FaceForensics++.'
Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.
You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.
Journal articles on the topic "FaceForensics++"
1
Hubálovský, Štěpán, Pavel Trojovský, Nebojsa Bacanin, and Venkatachalam K. "Evaluation of deepfake detection using YOLO with local binary pattern histogram." PeerJ Computer Science 8 (September 13, 2022): e1086. http://dx.doi.org/10.7717/peerj-cs.1086.
Full textAbstract:
Recently, deepfake technology has become a popularly used technique for swapping faces in images or videos that create forged data to mislead society. Detecting the originality of the video is a critical process due to the negative pattern of the image. In the detection of forged images or videos, various image processing techniques were implemented. Existing methods are ineffective in detecting new threats or false images. This article has proposed You Only Look Once–Local Binary Pattern Histogram (YOLO-LBPH) to detect fake videos. YOLO is used to detect the face in an image or a frame of a video. The spatial features are extracted from the face image using a EfficientNet-B5 method. Spatial feature extractions are fed as input in the Local Binary Pattern Histogram to extract temporal features. The proposed YOLO-LBPH is implemented using the large scale deepfake forensics (DF) dataset known as CelebDF-FaceForensics++(c23), which is a combination of FaceForensics++(c23) and Celeb-DF. As a result, the precision score is 86.88% in the CelebDF-FaceForensics++(c23) dataset, 88.9% in the DFFD dataset, 91.35% in the CASIA-WebFace data. Similarly, the recall is 92.45% in the Celeb-DF-Face Forensics ++(c23) dataset, 93.76% in the DFFD dataset, and 94.35% in the CASIA-Web Face dataset.
2
Ahmad, Wasim, Imad Ali, Sahibzada Adil Shahzad, Ammarah Hashmi, and Faisal Ghaffar. "ResViT." International journal of electrical and computer engineering systems 13, no. 9 (2022): 807–13. http://dx.doi.org/10.32985/ijeces.13.9.9.
Full textAbstract:
Deepfake makes it quite easy to synthesize videos or images using deep learning techniques, which leads to substantial danger and worry for most of the world's renowned people. Spreading false news or synthesizing one's video or image can harm people and their lack of trust on social and electronic media. To efficiently identify deepfake images, we propose ResViT, which uses the ResNet model for feature extraction, while the vision transformer is used for classification. The ResViT architecture uses the feature extractor to extract features from the images of the videos, which are used to classify the input as fake or real. Moreover, the ResViT architectures focus equally on data pre-processing, as it improves performance. We conducted extensive experiments on the five mostly used datasets our results with the baseline model on the following datasets of Celeb-DF, Celeb-DFv2, FaceForensics++, FF-Deepfake Detection, and DFDC2. Our analysis revealed that ResViT performed better than the baseline and achieved the prediction accuracy of 80.48%, 87.23%, 75.62%, 78.45%, and 84.55% on Celeb-DF, Celeb-DFv2, FaceForensics++, FF-Deepfake Detection, and DFDC2 datasets, respectively.
3
Javed, Muhammad, Zhaohui Zhang, Fida Hussain Dahri, and Asif Ali Laghari. "Real-Time Deepfake Video Detection Using Eye Movement Analysis with a Hybrid Deep Learning Approach." Electronics 13, no. 15 (2024): 2947. http://dx.doi.org/10.3390/electronics13152947.
Full textAbstract:
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.
4
Wang, Bo, Yucai Li, Xiaohan Wu, Yanyan Ma, Zengren Song, and Mingkan Wu. "Face Forgery Detection Based on the Improved Siamese Network." Security and Communication Networks 2022 (February 5, 2022): 1–13. http://dx.doi.org/10.1155/2022/5169873.
Full textAbstract:
Face tampering is an intriguing task in video/image genuineness identification and has attracted significant amounts of attention in recent years. In this work, we propose a face forgery detection method that consists of preprocessing, an improved Siamese network-based feature extractor (including a feature alignment module), and postprocessing (a voting principle). Roughly speaking, our method extracts the features in the grey space of face/background image pairs and measures the difference to make decisions. Experiments on several standard databases prove the effectiveness of our method, and especially on the low-quality subdataset of the FaceForensics++ , our method achieves a competitive result.
5
Borade, Shwetambari, Nilakshi Jain, Bhavesh Patel, et al. "ResNet50 DeepFake Detector: Unmasking Reality." Indian Journal Of Science And Technology 17, no. 13 (2024): 1263–71. http://dx.doi.org/10.17485/ijst/v17i13.285.
Full textAbstract:
Objectives: The objective of this research is to detect video deepfakes with a higher accuracy and provide optimum results. The research aims to reduce time complexity for the media processing while simultaneously working on the model accuracy. Methods: This research has utilized CelebDF and FaceForensics++ Datasets for training and 32 epochs with the use of Single Nvidia Tesla T4 GPU. The above method of training and validating the model yielded error of <5% and is very capable. Using image scraping this model initially eliminates the unimportant areas of consideration. Thus, reducing the amount of scans that the model does in order to identify the face. This reduces that training to graph ratio and provides less error margin. Findings: This research’s findings reveal the model's robustness in detecting manipulated videos generated by deepfake techniques. Through extensive experimentation on diverse datasets, ResNet50 consistently demonstrated 97% accuracy, sensitivity, and specificity in distinguishing authentic content from deepfakes. The model exhibited exceptional generalization across various scenarios, including face-swapping and lip-syncing, showcasing its adaptability to evolving deepfake techniques. This research contributes to the already existing literature on ResNet50 deepfake detection tools. It contributes by adding the image scraping feature to the ResNet50 model and overcomes the gaps such as increasing error percentage of some of the models. The research of 1 has a 20% error percentage while this research has an error percentage of 5% with an accuracy of 97%. Novelty: The study employs ResNet50 to detect deepfake videos, utilizing novel image scraping techniques to minimize errors and enhance prediction accuracy. Keywords: Deepfakes, Deep Learning, GAN, ResNet50, FaceForensics++, CelebDF
6
Karaköse, Mehmet, İsmail İlhan, Hasan Yetiş, and Serhat Ataş. "A New Approach for Deepfake Detection with the Choquet Fuzzy Integral." Applied Sciences 14, no. 16 (2024): 7216. http://dx.doi.org/10.3390/app14167216.
Full textAbstract:
Deepfakes have become widespread and have continued to develop rapidly in recent years. In addition to the use of deepfakes in movies and for humorous purposes, this technology has also begun to pose a threat to many companies and politicians. Deepfake detection is critical to the prevention of this threat. In this study, a Choquet fuzzy integral-based deepfake detection method is proposed to increase overall performance by combining the results obtained from different deepfake detection methods. Three different deepfake detection models were used in the study: XceptionNet, which has better performance in detecting real images/videos; EfficientNet, which has better performance in detecting fake videos; and a model based on their hybrid uses. The proposed method based on the Choquet fuzzy integral aims to eliminate the shortcomings of these methods by using each of the other methods. As a result, a higher performance was achieved with the proposed method than found when all three methods were used individually. As a result of the testing and validation studies carried out on FaceForensics++, DFDC, Celeb-DF, and DeepFake-TIMIT datasets, the individual performance levels of the algorithms used were 81.34%, 82.78%, and 79.15% on average, according to the AUC curve, while the level of 97.79% was reached with the proposed method. Considering that the average performance of the three methods across all datasets is 81.09%, it can be seen that an improvement of approximately 16.7% is achieved. In the FaceForensics++ dataset, in which individual algorithms are more successful, the performance of the proposed method reaches the highest AUC value, 99.8%. It can be seen that the performance rates can be increased by changing the individual methods discussed in the proposed method. We believe that the proposed method will inspire researchers and will be further developed.
7
Shwetambari, Borade, Jain Nilakshi, Patel Bhavesh, et al. "ResNet50 DeepFake Detector: Unmasking Reality." Indian Journal of Science and Technology 17, no. 13 (2024): 1263–71. https://doi.org/10.17485/IJST/v17i13.285.
Full textAbstract:
Abstract <strong>Objectives:</strong> The objective of this research is to detect video deepfakes with a higher accuracy and provide optimum results. The research aims to reduce time complexity for the media processing while simultaneously working on the model accuracy. <strong>Methods:</strong> This research has utilized CelebDF and FaceForensics++ Datasets for training and 32 epochs with the use of Single Nvidia Tesla T4 GPU. The above method of training and validating the model yielded error of <5% and is very capable. Using image scraping this model initially eliminates the unimportant areas of consideration. Thus, reducing the amount of scans that the model does in order to identify the face. This reduces that training to graph ratio and provides less error margin. <strong>Findings:</strong> This research’s findings reveal the model's robustness in detecting manipulated videos generated by deepfake techniques. Through extensive experimentation on diverse datasets, ResNet50 consistently demonstrated 97% accuracy, sensitivity, and specificity in distinguishing authentic content from deepfakes. The model exhibited exceptional generalization across various scenarios, including face-swapping and lip-syncing, showcasing its adaptability to evolving deepfake techniques. This research contributes to the already existing literature on ResNet50 deepfake detection tools. It contributes by adding the image scraping feature to the ResNet50 model and overcomes the gaps such as increasing error percentage of some of the models. The research of 1 has a 20% error percentage while this research has an error percentage of 5% with an accuracy of 97%. <strong>Novelty:</strong> The study employs ResNet50 to detect deepfake videos, utilizing novel image scraping techniques to minimize errors and enhance prediction accuracy. <strong>Keywords:</strong> Deepfakes, Deep Learning, GAN, ResNet50, FaceForensics++, CelebDF
8
Dumane, Ashwin. "AI-Powered Detection of Cyber Attacks: Addressing Deepfakes and Identity Theft." International Journal for Research in Applied Science and Engineering Technology 13, no. 6 (2025): 1569–73. https://doi.org/10.22214/ijraset.2025.72416.
Full textAbstract:
The proliferation of deepfake technologies has introduced significant challenges to cybersecurity, facilitating sophisticated identity fraud and misinformation dissemination. This study presents a comprehensive AI-driven detection framework that integrates convolutional neural networks (CNNs), ensemble classifiers, and behavioral analysis for the identification of manipulated multimedia content and identity theft. Utilizing datasets such as DFDC, FaceForensics++, and a custom identity fraud dataset, the system employs Preprocessing techniques including normalization, augmentation, and Error Level Analysis (ELA). Experimental results demonstrate 97% accuracy for visual deepfake detection, 98.5% for audio stream analysis, and 91.7% for identity fraud detection using Capsule Networks. These findings underscore the potential of the proposed architecture in real-time cyber threat mitigation and offer a foundation for future AI-based forensic systems.
9
Petmezas, Georgios, Vazgken Vanian, Manuel Pastor Rufete, Eleana E. I. Almaloglou, and Dimitris Zarpalas. "A Dual-Branch Fusion Model for Deepfake Detection Using Video Frames and Microexpression Features." Journal of Imaging 11, no. 7 (2025): 231. https://doi.org/10.3390/jimaging11070231.
Full textAbstract:
Deepfake detection has become a critical issue due to the rise of synthetic media and its potential for misuse. In this paper, we propose a novel approach to deepfake detection by combining video frame analysis with facial microexpression features. The dual-branch fusion model utilizes a 3D ResNet18 for spatiotemporal feature extraction and a transformer model to capture microexpression patterns, which are difficult to replicate in manipulated content. We evaluate the model on the widely used FaceForensics++ (FF++) dataset and demonstrate that our approach outperforms existing state-of-the-art methods, achieving 99.81% accuracy and a perfect ROC-AUC score of 100%. The proposed method highlights the importance of integrating diverse data sources for deepfake detection, addressing some of the current limitations of existing systems.
10
K. Alzurf, Noor, and Mohammed S. Altaei. "Efficiency Evaluation of Popular Deepfake Methods Using Convolution Neural Network." Al-Nahrain Journal of Science 26, no. 3 (2023): 44–50. http://dx.doi.org/10.22401/anjs.26.3.07.
Full textAbstract:
Many deepfake techniques in the early years are spread to create successful deepfake videos (i.e., Face Swap, Deep Fake, etc.). These methods enable anyone to manipulate faces in videos, which can negatively impact society. One way to reduce this problem is the deepfake detection. It has become such a hot topic and the most crucial task in recent years. This paper proposes a deep learning model to detect and evaluate deepfake video methods using convolutional neural networks. The model is evaluated on the FaceForensics++ video dataset that contains four different deepfake ways (deepfake, face 2 face, face swap, and neuraltexture), and it achieved 0.96 accuracy on the deepfake method, 0.95 accuracy on face 2 face approach, 0.94 precision on face swap method and 0.76 accuracy on neuraltexture method.
Book chapters on the topic "FaceForensics++"
1
Roy, Ritaban, Indu Joshi, Abhijit Das, and Antitza Dantcheva. "3D CNN Architectures and Attention Mechanisms for Deepfake Detection." In Handbook of Digital Face Manipulation and Detection. Springer International Publishing, 2022. http://dx.doi.org/10.1007/978-3-030-87664-7_10.
Full textAbstract:
AbstractManipulated images and videos have become increasingly realistic due to the tremendous progress of deep convolutional neural networks (CNNs). While technically intriguing, such progress raises a number of social concerns related to the advent and spread of fake information and fake news. Such concerns necessitate the introduction of robust and reliable methods for fake image and video detection. Toward this in this work, we study the ability of state-of-the-art video CNNs including 3D ResNet, 3D ResNeXt, and I3D in detecting manipulated videos. In addition, and toward a more robust detection, we investigate the effectiveness of attention mechanisms in this context. Such mechanisms are introduced in CNN architectures in order to ensure that robust features are being learnt. We test two attention mechanisms, namely SE-block and Non-local networks. We present related experimental results on videos tampered by four manipulation techniques, as included in the FaceForensics++ dataset. We investigate three scenarios, where the networks are trained to detect (a) all manipulated videos, (b) each manipulation technique individually, as well as (c) the veracity of videos pertaining to manipulation techniques not included in the train set.
2
Choudhary, Shilpa. "Advancing Deep Fake Detection Using a Comprehensive Analysis With Hyper-Tuned ResNet-50." In Advances in Computational Intelligence and Robotics. IGI Global, 2025. https://doi.org/10.4018/979-8-3693-7575-4.ch002.
Full textAbstract:
In this study, the authors explored deepfake detection using ResNet-50 model, with a focus on the role of data preprocessing and augmentation in improving model's robustness. Two datasets, FaceForensics++ and CelebDF, which incorporate manipulated images with differently-applied manipulations have been used in the study. The addition of contrast normalization along with noise reduction and data augmentation in the forms of rotation, flipping, scaling led to the improvement in model's performance with very high accuracies of 94.27% and 94.02%; precision and recall rates, in this case, exceed 92%. These results imply that the model can be reliably and efficiently used in developing high-performance neural network-based detection systems of deepfake media.
3
P, Mrs Sujitha, and Dr Priya R. "ROBUST DETECTION OF INTRA-FRAME COPY-MOVE FORGERIES IN DIGITAL VIDEOS." In AI in Industry 5.0: Revolutionizing Business and Technology. Royal Book Publishing, 2025. https://doi.org/10.26524/royal.239.5.
Full textAbstract:
With over 3.7 million videos shared daily on platforms like YouTube and social media, the proliferation of high-quality forged videos is rapidly increasing. Such forgeries compromise the authenticity and integrity of digital evidence, potentially leading to serious consequences. For instance, in judicial proceedings, a tampered video used as evidence could wrongfully implicate an innocent person or help a guilty individual evade justice. This necessitates robust detection mechanisms to counteract forgery attempts. One prevalent method of forgery is copy-move video forgery, which involves duplicating regions within a single video frame or across consecutive frames. Traditional detection approaches rely on manual pattern recognition and block-matching, often yielding detection accuracies below 70%, particularly in high-resolution and compressed videos. In contrast, deep learning-based techniques have shown significantly improved performance, with Convolutional Neural Network (CNN) and Transformer-based models achieving up to 92.6% accuracy on standard datasets like Kaggle and FaceForensics++. This research leverages pre-trained deep learning architectures to automatically learn discriminative features, enhancing the detection of copy-move forgery in complex and dynamic video environments.
4
Jimenez-Martinez, Miguel, Gibran Benitez-Garcia, Linda Karina Toscano-Medina, and Jesus Olivares-Mercado. "Frame-Level Deepfake Detection on Explicit Content with ID-Unaware Binary Classification." In Frontiers in Artificial Intelligence and Applications. IOS Press, 2024. http://dx.doi.org/10.3233/faia240353.
Full textAbstract:
The rapid advancement in deepfake technology has enabled the creation of highly realistic fake images and videos, posing significant risks, especially in the context of explicit content. Such content, which often involves the alteration of an individual’s identity in sexually explicit material, can lead to defamation, harassment, and blackmail. This paper focuses on the detection of deepfakes in explicit content using a state-of-the-art ID-unaware Binary Classification method. We evaluate its effectiveness in real-world scenarios by analyzing three versions of the model with different backbones: ResNet34, EfficientNet-B3, and EfficientNet-B4. To facilitate this evaluation, we curated a dataset of 200 videos, consisting of 100 genuine videos and their corresponding deepfake counterparts, ensuring a direct comparison between genuine and altered content. Our analysis revealed a significant decrease in detection performance when applying the state-of-the-art method to explicit content. Specifically, the AUC score dropped from 93% on standard datasets such as FaceForensics++ to 62% on our explicit content dataset. Additionally, the accuracy for detecting deepfakes plummeted to around 25%, while the accuracy for genuine videos remained high at approximately 90%. We identified specific factors contributing to this decline, including unconventional makeup, lighting issues, and facial blurring due to camera distance. These findings underscore the challenges and the necessity for robust detection methods to address the unique problems posed by explicit content deepfakes, ultimately aiming to protect individuals from the potential harms associated with this technology.
Conference papers on the topic "FaceForensics++"
1
Rossler, Andreas, Davide Cozzolino, Luisa Verdoliva, Christian Riess, Justus Thies, and Matthias Niessner. "FaceForensics++: Learning to Detect Manipulated Facial Images." In 2019 IEEE/CVF International Conference on Computer Vision (ICCV). IEEE, 2019. http://dx.doi.org/10.1109/iccv.2019.00009.
Full text
2
Markelj, Bine, Peter Peer, and Borut Batagelj. "Ustvarjanje ponarejenih videoposnetkov s pomočjo difuzijskih modelov." In Strokovna konferenca ROSUS 2024: Računalniška obdelava slik in njena uporaba v Sloveniji 2024. Univerza v Mariboru, Univerzitetna založba, 2024. http://dx.doi.org/10.18690/um.feri.1.2024.8.
Full textAbstract:
V članku predstavimo postopke in tehnike generiranja globoko ponarejenih videoposnetkov ali krajše globokih ponaredkov (angl. deepfakes). To so videoposnetki, pri katerih je prišlo do manipulacij s tehnikami globokega učenja. Taki videoposnetki predstavljajo velik problem pri širjenju lažnih novic, politični propagandi, uničevanju podobe posameznikov, izdelavi pornografskih vsebin, izsiljevanju itd. V članku opišemo podatkovno zbirko FaceForensics++ in predstavimo lastno metodo za potencialno izdelavo podzbirke omenjene baze z uporabo najnovejših generativnih difuzijskih modelov. Uporabljene postopke eksperimenta predstavimo in analiziramo njihovo kvaliteto in uspešnost. Komentiramo tudi smiselnost uporabe in nevarnost, ki jo predstavljajo ponarejeni videoposnetki, izdelani z difuzijskimi modeli.
3
da Rosa, Lucas Migliorin, and Carlos Mauricio Serodio Figueiredo. "Application of Digital Image Processing in a Deepfake Detection Network." In Encontro Nacional de Inteligência Artificial e Computacional. Sociedade Brasileira de Computação - SBC, 2023. http://dx.doi.org/10.5753/eniac.2023.234266.
Full textAbstract:
A evolução das redes Generative Adversarial Networks (GANs) abre um leque de possibilidades para que usuários mal intencionados aproveitem essa tecnologia a fim extrair informações de outros usuários e falsificando suas identidades. Ferramentas, como DeepFaceLab é um exemplo da utilização dessas redes a fim de criar Deepfakes cada vez mais realísticos no qual permite que a troca dos rostos das pessoas em imagens ou vídeos seja cada vez mais fácil. O presente trabalho apresenta uma evolução de modelos de detecção de deepfakes por meio da aplicação de técnicas de processamento digital de imagens e evolução de modelos da literatura aplicando backbones convolucionais mais atuais. Tais modelos são avaliados em datasets da literatura como o Deepfake Detection Challenge e Faceforensics++.
4
Trinh, Loc, and Yan Liu. "An Examination of Fairness of AI Models for Deepfake Detection." In Thirtieth International Joint Conference on Artificial Intelligence {IJCAI-21}. International Joint Conferences on Artificial Intelligence Organization, 2021. http://dx.doi.org/10.24963/ijcai.2021/79.
Full textAbstract:
Recent studies have demonstrated that deep learning models can discriminate based on protected classes like race and gender. In this work, we evaluate bias present in deepfake datasets and detection models across protected subgroups. Using facial datasets balanced by race and gender, we examine three popular deepfake detectors and find large disparities in predictive performances across races, with up to 10.7% difference in error rate between subgroups. A closer look reveals that the widely used FaceForensics++ dataset is overwhelmingly composed of Caucasian subjects, with the majority being female Caucasians. Our investigation of the racial distribution of deepfakes reveals that the methods used to create deepfakes as positive training signals tend to produce ``irregular" faces - when a person’s face is swapped onto another person of a different race or gender. This causes detectors to learn spurious correlations between the foreground faces and fakeness. Moreover, when detectors are trained with the Blended Image (BI) dataset from Face X-Rays, we find that those detectors develop systematic discrimination towards certain racial subgroups, primarily female Asians.
5
Hu, Ziheng, Hongtao Xie, YuXin Wang, Jiahong Li, Zhongyuan Wang, and Yongdong Zhang. "Dynamic Inconsistency-aware DeepFake Video Detection." In Thirtieth International Joint Conference on Artificial Intelligence {IJCAI-21}. International Joint Conferences on Artificial Intelligence Organization, 2021. http://dx.doi.org/10.24963/ijcai.2021/102.
Full textAbstract:
The spread of DeepFake videos causes a serious threat to information security, calling for effective detection methods to distinguish them. However, the performance of recent frame-based detection methods become limited due to their ignorance of the inter-frame inconsistency of fake videos. In this paper, we propose a novel Dynamic Inconsistency-aware Network to handle the inconsistent problem, which uses a Cross-Reference module (CRM) to capture both the global and local inter-frame inconsistencies. The CRM contains two parallel branches. The first branch takes faces from adjacent frames as input, and calculates a structure similarity map for a global inconsistency representation. The second branch only focuses on the inter-frame variation of independent critical regions, which captures the local inconsistency. To the best of our knowledge, this is the first work to totally use the inter-frame inconsistency information from the global and local perspectives. Compared with existing methods, our model provides a more accurate and robust detection on FaceForensics++, DFDC-preview and Celeb-DFv2 datasets.