FDFtNet: Facing Off Fake Images Using Fake Detection Fine-Tuning Network
Open accessThe DOI matches its Crossref record; 30 of the 32 references it cites were found in a registry or an index.
Abstract
Creating fake images and videos such as “Deepfake” has become much easier these days due to the advancement in Generative Adversarial Networks (GANs). Moreover, recent research such as the few-shot learning can create highly realistic personalized fake images with only a few images. Therefore, the threat of Deepfake to be used for a variety of malicious intents such as propagating fake images and videos becomes prevalent. And detecting these machine-generated fake images has been more challenging than ever. In this work, we propose a light-weight robust fine-tuning neural network-based classifier architecture called Fake Detection Fine-tuning Network (FDFtNet), which is capable of detecting many of the new fake face image generation models, and can be easily combined with existing image classification networks and fine-tuned on a few datasets. In contrast to many existing methods, our approach aims to reuse popular pre-trained models with only a few images for fine-tuning to effectively detect fake images. The core of our approach is to introduce an image-based self-attention module called Fine-Tune Transformer that uses only the attention module and the down-sampling layer. This module is added to the pre-trained model and fine-tuned on a few data to search for new sets of feature space to detect fake images. We experiment with our FDFtNet on the GANs-based dataset (Progressive Growing GAN) and Deepfake-based dataset (Deepfake and Face2Face) with a small input image resolution of 64\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\times $$\end{document}×64 that complicates detection. Our FDFtNet achieves an overall accuracy of 90.29% in detecting fake images generated from the GANs-based dataset, outperforming the state-of-the-art.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“As far as we know, current deep learning methods do not fully use the three semantics of images.”
From Multisemantic Path Neural Network for Deepfake Detection (2022) · cites this paper as [40]
Citations
Cites
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474 · cited 1×
“Figure 1 shows an overview of our approach, where we utilize wellknown, existing CNN architectures [27,29,6,12,11,10] for fake image detection.”
Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, L., & Polosukhin, I. (2017) · arXiv · doi:10.48550/arxiv.1706.03762 · Cited by 120,404 · cited 1×
“This approach is similar to the Multi-head Attention Module [32] (Query, key, and Value), but the difference is that FTT is suitable for the image to be applied to the 1×1 convolution.”
Very Deep Convolutional Networks for Large-Scale Image Recognition
Simonyan, K., & Zisserman, A. (2014) · arXiv · doi:10.48550/arxiv.1409.1556 · Cited by 114,148 · cited 1×
“Figure 1 shows an overview of our approach, where we utilize well-known, existing CNN architectures [27,29,7,13,12,11] for fake image detection.”
Going deeper with convolutions
Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., & Rabinovich, A. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298594 · Cited by 48,562
Squeeze-and-Excitation Networks
Hu, J., Shen, L., & Sun, G. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00745 · Cited by 35,667
MobileNetV2: Inverted Residuals and Linear Bottlenecks
Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., & Chen, L.-C. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00474 · Cited by 28,755 · cited 1×
“We chose MobileNet block V3 (MBblockV3) to explore the image feature space through inverted residual structure and linear bottleneck [25].”
MethodXception: Deep Learning with Depthwise Separable Convolutions
Chollet, F. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.195 · Cited by 20,380 · cited 1×
“Xception [1] has been served as the baseline for fake image detection in [30,23].”
GAN(Generative Adversarial Nets)
(2017) · Journal of Japan Society for Fuzzy Theory and Intelligent Informatics · doi:10.3156/jsoft.29.5_177_2 · Cited by 19,270
MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
Howard, A. G., Zhu, M., Chen, B., Kalenichenko, D., Wang, W., Weyand, T., Andreetto, M., & Adam, H. (2017) · arXiv · doi:10.48550/arxiv.1704.04861 · Cited by 19,015 · cited 2×
“Depthwise separable convolutions, as in Xception and MobileNetV1 [11], are also included in MBblockV3.”
BackgroundBatch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
Ioffe, S. (2024) · arXiv (Cornell University) · doi:10.57702/o9raffed · Cited by 14,214
Squeeze-and-Excitation Networks
Hu, J., Shen, L., Albanie, S., Sun, G., & Wu, E. (2020) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2019.2913372 · Cited by 12,157
A Style-Based Generator Architecture for Generative Adversarial Networks
Karras, T., Laine, S., & Aila, T. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00453 · Cited by 11,714 · cited 1×
“The emergence of Generative Adversarial Networks (GANs) [5], which produces high-quality images through a generator and a discriminator that is trained adversely and competitively, enables the generated outputs to be highly realistic and sophisticated [16,38,17,34].”
Identity mappings in deep residual networks
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-46493-0_38 · Cited by 10,741
Deep Learning Face Attributes in the Wild
Liu, Z., Luo, P., Wang, X., & Tang, X. (2015) · 2015 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.425 · Cited by 7,747
SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size
Iandola, F. N., Han, S., Moskewicz, M. W., Ashraf, K., Dally, W. J., & Keutzer, K. (2016) · arXiv · doi:10.48550/arxiv.1602.07360 · Cited by 6,201 · cited 8×
“SqueezeNet.”
BackgroundInfluentialSelf-Attention Generative Adversarial Networks
Zhang, H., Goodfellow, I., Metaxas, D., & Odena, A. (2018) · arXiv · doi:10.48550/arxiv.1805.08318 · Cited by 3,353
FaceForensics++: Learning to Detect Manipulated Facial Images
Rossler, A., Cozzolino, D., Verdoliva, L., Riess, C., Thies, J., & Niessner, M. (2019) · 2019 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00009 · Cited by 3,314 · cited 2×
“FaceForensic++ [24] proposed a forgery detection method tailored to facial manipulations and provided an extensive evaluation in a supervised manner.”
BackgroundMethodSearching for activation functions
Ramachandran, P., Zoph, B., & Le, Q. V. (2017) · arXiv · doi:10.48550/arxiv.1710.05941 · Cited by 2,335 · cited 1×
“This non-FDFtNet”
Sigmoid-Weighted Linear Units for Neural Network Function Approximation in Reinforcement Learning
Elfwing, S., Uchibe, E., & Doya, K. (2018) · Neural Networks · doi:10.1016/j.neunet.2017.12.012 · Cited by 2,119
Face2Face: Real-Time Face Capture and Reenactment of RGB Videos
Thies, J., Zollhofer, M., Stamminger, M., Theobalt, C., & Niessner, M. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.262 · Cited by 1,747
Meta-Transfer Learning for Few-Shot Learning
Sun, Q., Liu, Y., Chua, T.-S., & Schiele, B. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00049 · Cited by 1,264 · cited 1×
“Furthermore, a recent study using the few-shot learning technique [28] in GAN allows Deep Learning models to produce high-quality outputs with only a small amount of training data.”
Bridging Nonlinearities and Stochastic Regularizers with Gaussian Error Linear UnitsPreprint
Hendrycks, D., & Gimpel, K. (2016) · arXiv (Cornell University) · Cited by 1,156
Few-Shot Adversarial Learning of Realistic Neural Talking Head Models
Zakharov, E., Shysheya, A., Burkov, E., & Lempitsky, V. (2019) · 2019 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00955 · Cited by 687 · cited 1×
“[38] demonstrated that models capable of generating highly realistic personalized talking head faces could be constructed using few-shot learning techniques, where the training inputs provide attention to the generator as a compressed form of feature landmarks, extracted through embedding layers.”
BackgroundExposing Digital Forgeries From JPEG Ghosts
Farid, H. (2009) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2008.2012215 · Cited by 449
Attributing Fake Images to GANs: Learning and Analyzing GAN Fingerprints
Yu, N., Davis, L., & Fritz, M. (2019) · 2019 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00765 · Cited by 437 · cited 2×
“[37] used patterns from GAN generated fake to show improvement in detection.”
Sliced Wasserstein Generative Models
Wu, J., Huang, Z., Acharya, D., Li, W., Thoma, J., Paudel, D. P., & Gool, L. V. (2019) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2019.00383 · Cited by 171 · cited 1×
“The emergence of Generative Adversarial Networks (GANs) [5], which produces high-quality images through a generator and a discriminator that is trained adversely and competitively, enables the generated outputs to be highly realistic and sophisticated [16,38,17,34].”
A Quantization-Friendly Separable Convolution for MobileNets
Sheng, T., Feng, C., Zhuo, S., Zhang, X., Shen, L., & Aleksic, M. (2018) · 2018 1st Workshop on Energy Efficient Machine Learning and Cognitive Computing for Embedded Applications (EMC2) · doi:10.1109/emc2.2018.00011 · Cited by 76 · cited 1×
“Since clipping the input values at the bottom layers may have a side effect of distorting the data distribution [26], we apply these activation functions at the top layers to reduce distortion and extract different signals from ReLU.”
MethodGAN is a friend or foe?: a framework to detect various fake face images
Tariq, S., Lee, S., Kim, H., Shin, Y., & Woo, S. S. (2019) · Proceedings of the 34th ACM/SIGAPP Symposium on Applied Computing · doi:10.1145/3297280.3297410 · Cited by 66
Self-citationJeon, H., Bang, Y., & Woo, S. S. (2019) · 2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW) · doi:10.1109/iccvw.2019.00163 · Cited by 26 · cited 2×
“Recent models, such as ShallowNet [30] and FakeTalkerDetect [15], used neural networks to detect GANs-generated fake images Yu et al.”
Self-citationEstimating Distribution Costs with the E aton– K ortum Model
Yang, X. (2015) · Review of Development Economics · doi:10.1111/rode.12160 · Cited by 2 · cited 1×
“Many researchers [5, 20, 38, 23] have investigated various digital forensics algorithms to detect forged images.”
Background
Research works printed but not linked: 8
- DeVries, T., Taylor, G.W.: Improved regularization of convolutional neural networks with cutout (2017). arXiv preprint arXiv:1708.04552 · arXiv
- Goodfellow, I., et al.: Generative adversarial nets. In: Advances in Neural Information Processing Systems, pp. 2672–2680 (2014)
- Howard, A., et al.: Searching for mobilenetv3. arXiv preprint arXiv:1905.02244 (2019) · arXiv
- Iandola, F., Moskewicz, M., Karayev, S., Girshick, R., Darrell, T., Keutzer, K.: Densenet: implementing efficient convnet descriptor pyramids (2014). arXiv preprint arXiv:1404.1869 · arXiv
- Karras, T., Aila, T., Laine, S., Lehtinen, J.: Progressive growing of gans for improved quality, stability, and variation (2017). arXiv preprint arXiv:1710.10196 · arXiv
- Krawetz, N., Solutions, H.F.: A picture’s worth. Hacker Factor Solutions 6, 2 (2007)
- Mankar, S.K., Gurjar, A.A.: Image forgery types and their detection: a review. Int. J. Adv. Res. Comput. Sci. Softw. Eng. 5(4), 174–178 (2015)
- Rössler, A., Cozzolino, D., Verdoliva, L., Riess, C., Thies, J., Nießner, M.: Faceforensics: a large-scale video dataset for forgery detection in human faces (2018). arXiv preprint arXiv:1803.09179 · arXiv
Cited by
Thinking in Frequency: Face Forgery Detection by Mining Frequency-Aware Clues
Qian, Y., Yin, G., Sheng, L., Chen, Z., & Shao, J. (2020) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-58610-2_6 · Cited by 1,058
M2TR: Multi-modal Multi-scale Transformers for Deepfake Detection
Wang, J., Wu, Z., Ouyang, W., Han, X., Chen, J., Jiang, Y.-G., & Li, S.-N. (2022) · Proceedings of the 2022 International Conference on Multimedia Retrieval · doi:10.1145/3512527.3531415 · Cited by 368
“The above challenges have driven the development of Deepfake forensics using deep neural networks [1, 5, 25, 32, 34, 40, 67].”
BackgroundDeepFake Detection for Human Face Images and Videos: A Survey
Malik, A., Kuribayashi, M., Abdullahi, S. M., & Khan, A. N. (2022) · IEEE Access · doi:10.1109/access.2022.3151186 · Cited by 297
“[73] introduced an FDFtNet method to improve the capability of existing CNN models, such as SqueezeNet, ShallowNetV3, ResNetV2, and Xception.”
MethodCountering Malicious DeepFakes: Survey, Battleground, and Horizon
Juefei-Xu, F., Wang, R., Huang, Y., Guo, Q., Ma, L., & Liu, Y. (2022) · International Journal of Computer Vision · doi:10.1007/s11263-022-01606-8 · Cited by 191
“Due to the significant progress of DNN models in various cutting-edge fields, powerful DNN models are designed or employed for spotting DeepFakes, such as FDFtNet (Jeon et al., 2020b) or ResNet-50 (Wang et al., 2020e).”
BackgroundMethodInfluentialFReTAL: Generalizing Deepfake Detection using Knowledge Distillation and Representation Learning
Kim, M., Tariq, S., & Woo, S. S. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw53098.2021.00111 · Cited by 118
“These methods include splice detection [88, 89, 8, 7, 30, 70], abnormal eye blinking [50], signal level artifacts [55, 51], irregular head poses [84], peculiar behavior patterns [3, 2], and many other data-driven methods that do not rely on particular traces or artifacts in the deepfake videos [75, 76, 77, 47, 46, 41,…”
MethodSelf-citation
Metadata
- Authors
- Jeon, H., Bang, Y., & Woo, S. S.
- Affiliations
- Sungkyunkwan University (KR)
- Corresponding author
- Woo, Simon S.
- Venue
- IFIP Advances in Information and Communication Technology
- Publisher
- Springer International Publishing
- Published
- 2020
- Volume
- AICT-580
- Pages
- 416-430
- ISSN
- 1868-422X (ISSN-L)
- 1868-4238
- OpenAlex
- W3086623482
- Cited by
- 65
- References
- 32
- Citations by year
- 2026: 2 · 2025: 10 · 2024: 11 · 2023: 13 · 2022: 18 · 2021: 7 · 2020: 4
- FWCI
- 3.24
- Type
- conference paper
- Language
- en
- Open access
- green
- arxiv.org
- Licence
- www.springernature.com/gp/researchers/text-and-data-mining (tdm)
- www.springernature.com/gp/researchers/text-and-data-mining (vor)
- Locations
- IFIP advances in information and communication technology (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- HAL (submittedVersion, cc-by)
- arXiv (Cornell University)
- Funders
- National Research Foundation
- Sungkyunkwan University (2019-0-00421)
- National Research Foundation of Korea (2020R1C1C1006004, 2019M3F2A1072217, 2019-0-00421, 2017R1C1B5076474)
- Ministry of Science and ICT, South Korea (2019-0-00421)
- Institute for Information and Communications Technology Promotion (2019‐0‐00421)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Digital Media Forensic Detection
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Generative Adversarial Networks and Image Synthesis
- Social Sciences › Sociology and Political Science › Misinformation and Its Impacts
- Keywords
- deepfake detection, fake image detection, fine-tuning, transformer models, few-shot learning, generative adversarial networks, Face2Face, lightweight neural networks
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.