[Retracted] Comparative Analysis of Deepfake Image Detection Method Using Convolutional Neural Network
Open accessThe DOI matches its Crossref record; 25 of the 25 references it cites were found in a registry or an index.
Abstract
Generation Z is a data‐driven generation. Everyone has the entirety of humanity’s knowledge in their hands. The technological possibilities are endless. However, we use and misuse this blessing to face swap using deepfake. Deepfake is an emerging subdomain of artificial intelligence technology in which one person’s face is overlaid over another person’s face, which is very prominent across social media. Machine learning is the main element of deepfakes, and it has allowed deepfake images and videos to be generated considerably faster and at a lower cost. Despite the negative connotations associated with the phrase “deepfakes,” the technology is being more widely employed commercially and individually. Although it is relatively new, the latest technological advances make it more and more challenging to detect deepfakes and synthesized images from real ones. An increasing sense of unease has developed around the emergence of deepfake technologies. Our main objective is to detect deepfake images from real ones accurately. In this research, we implemented several methods to detect deepfake images and make a comparative analysis. Our model was trained by datasets from Kaggle, which had 70,000 images from the Flickr dataset and 70,000 images produced by styleGAN. For this comparative study of the use of convolutional neural networks (CNN) to identify genuine and deepfake pictures, we trained eight different CNN models. Three of these models were trained using the DenseNet architecture (DenseNet121, DenseNet169, and DenseNet201); two were trained using the VGGNet architecture (VGG16, VGG19); one was with the ResNet50 architecture, one with the VGGFace, and one with a bespoke CNN architecture. We have also implemented a custom model that incorporates methods like dropout and padding that aid in determining whether or not the other models reflect their objectives. The results were categorized by five evaluation metrics: accuracy, precision, recall, F 1‐score, and area under the ROC (receiver operating characteristic) curve. Amongst all the models, VGGFace performed the best, with 99% accuracy. Besides, we obtained 97% from the ResNet50, 96% from the DenseNet201, 95% from the DenseNet169, 94% from the VGG19, 92% from the VGG16, 97% from the DenseNet121 model, and 90% from the custom model.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
FaceNet: A unified embedding for face recognition and clustering
Schroff, F., Kalenichenko, D., & Philbin, J. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298682 · Cited by 15,267
Self-Attention Generative Adversarial Networks
Zhang, H., Goodfellow, I., Metaxas, D., & Odena, A. (2018) · arXiv · doi:10.48550/arxiv.1805.08318 · Cited by 3,353 · cited 2×
“Because deep learning algorithms like CNN and GAN can improve legibility, facial expression, and lighting in photos, swapped face images have become harder for forensics models [27].”
BackgroundMethodFaceForensics++: 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×
“…been observed. include the Idiap Research Institute replay-attack dataset [51], Afchar et al. deepfake’s face-swapping dataset [52], the facial re-enactment FaceForensics dataset [44], developed by the Face2Face technique [53], and Rahmouni et al. entirely computer-generated picture dataset [54].”
MethodMesoNet: a Compact Facial Video Forgery Detection Network
Afchar, D., Nozick, V., Yamagishi, J., & Echizen, I. (2018) · 2018 IEEE International Workshop on Information Forensics and Security (WIFS) · doi:10.1109/wifs.2018.8630761 · Cited by 1,872
Long-Term Recurrent Convolutional Networks for Visual Recognition and Description
Donahue, J., Hendricks, L. A., Rohrbach, M., Venugopalan, S., Guadarrama, S., Saenko, K., & Darrell, T. (2017) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2016.2599174 · Cited by 1,547
Hinton, G. E., Krizhevsky, A., & Wang, S. D. (2011) · Lecture Notes in Computer Science · doi:10.1007/978-3-642-21735-7_6 · Cited by 1,360 · cited 1×
“…[48] recommended using capsule networks. capsule network was created to overcome the constraints of CNNs when employed for inverse graphics tasks [49], which attempt to discover physical processes that form pictures of the environment. ability of a capsule network based on a dynamic routing…”
BackgroundDeepfakes and beyond: A Survey of face manipulation and fake detection
Tolosana, R., Vera-Rodriguez, R., Fierrez, J., Morales, A., & Ortega-Garcia, J. (2020) · Information Fusion · doi:10.1016/j.inffus.2020.06.014 · Cited by 1,237
The Emergence of Deepfake Technology: A Review
Westerlund, M. (2019) · Technology Innovation Management Review · doi:10.22215/timreview/1282 · Cited by 1,138
In Ictu Oculi: Exposing AI Created Fake Videos by Detecting Eye Blinking
Li, Y., Chang, M.-C., & Lyu, S. (2018) · 2018 IEEE International Workshop on Information Forensics and Security (WIFS) · doi:10.1109/wifs.2018.8630787 · Cited by 1,089
Capsule-forensics: Using Capsule Networks to Detect Forged Images and Videos
Nguyen, H. H., Yamagishi, J., & Echizen, I. (2019) · ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) · doi:10.1109/icassp.2019.8682602 · Cited by 951
Lip reading sentences in the wild
Chung, J. S., Senior, A., Vinyals, O., & Zisserman, A. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.367 · Cited by 702 · cited 1×
“When used to detect deepfake movies from this newly created dataset, other methods such as lip-syncing approaches [32–34] and picture quality measures with support vector machine (SVM) [35] generate very high error rates.”
MethodTwo-Stream Neural Networks for Tampered Face Detection
Zhou, P., Han, X., Morariu, V. I., & Davis, L. S. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw.2017.229 · Cited by 700
DeepFake Detection by Analyzing Convolutional Traces
Guarnera, L., Giudice, O., & Battiato, S. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw50498.2020.00341 · Cited by 374 · cited 1×
“For instance, Google has made a fake video database accessible for academicians to build new algorithms to detect deepfake, while Facebook and Microsoft have organized the Deepfake Detection Challenge [7].”
BackgroundMaras, M.-H., & Alexandrou, A. (2019) · The International Journal of Evidence & Proof · doi:10.1177/1365712718807226 · Cited by 343 · cited 1×
“Besides, Taylor Swift, Gal Gadot, Emma Watson, Meghan Markle, and many other celebrities have been victims of deepfake technology [5].”
BackgroundDeepVision: Deepfakes Detection Using Human Eye Blinking Pattern
Jung, T., Kim, S., & Kim, K. (2020) · IEEE Access · doi:10.1109/access.2020.2988660 · Cited by 326 · cited 1×
“Deepfakes have grown to be barely distinguishable from natural pictures as technology has progressed over the years [3].”
BackgroundUnsupervised speech representation learning using WaveNet autoencoders
Chorowski, J., Weiss, R. J., Bengio, S., & van den Oord, A. (2019) · IEEE/ACM Transactions on Audio, Speech, and Language Processing · doi:10.1109/taslp.2019.2938863 · Cited by 325 · cited 13×
“)ere are several methods to detect GAN-generated deepfake images, including the traditional machine learning classifiers (Support Vector Machine Algorithm, or naive algorithms), deep neural networks, convolutional neural networks (CNN), recurrent neural networks (RNN), long short-term memory (LSTM), and many more.”
MethodInfluentialDeep fake image detection based on pairwise learning
Hsu, C.-C., Zhuang, Y.-X., & Lee, C.-Y. (2020) · Applied Sciences · doi:10.3390/app10010370 · Cited by 304
Authentication theory and hypothesis testing
Maurer, U. M. (2000) · IEEE Transactions on Information Theory · doi:10.1109/18.850674 · Cited by 200 · cited 1×
“On the contrary, Agarwal and Varshney [30] framed the GAN-based deepfake detection problem as a hypothesis testing problem, using a statistical framework based on the information-theoretic study of authenticity [31].”
MethodVulnerability assessment and detection of Deepfake videos
Korshunov, P., & Marcel, S. (2019) · 2019 International Conference on Biometrics (ICB) · doi:10.1109/icb45273.2019.8987375 · Cited by 162 · cited 1×
“Korshunov and Marcel [23, 24] used the open-source code Faceswap-GAN [19] to create a unique deepfake dataset containing 620 videos based on the GAN model to address this issue.”
MethodAutomated face swapping and its detection
Zhang, Y., Zheng, L., & Thing, V. L. L. (2017) · 2017 IEEE 2nd International Conference on Signal and Image Processing (ICSIP) · doi:10.1109/siprocess.2017.8124497 · Cited by 154 · cited 1×
“In their paper [36], Zhang et al. utilized the bag of words approach to extract a collection of compact features, which they then put into classifiers like SVM [37], random forest (RF) [38], and multilayer per-ceptron (MLP) [39] to distinguish swapped face images from real ones.”
BackgroundDeepfakes Detection Techniques Using Deep Learning: A Survey
Almars, A. M. (2021) · Journal of Computer and Communications · doi:10.4236/jcc.2021.95003 · Cited by 143 · cited 1×
“In the United States and Asian societies, many women are also victimized by deep fake technologies. harmful use of deep fakes can sig-nificantly impact our culture and increase misleading information, especially on social media [6].”
BackgroundDeep learning for deepfakes creation and detection: a survey
Nguyen, T. T., Nguyen, Q. V. H., Nguyen, D. T., Nguyen, D. T., Huynh-The, T., Nahavandi, S., Nguyen, T. T., Pham, Q.-V., & Nguyen, C. M. (2022) · SSRN Electronic Journal · doi:10.2139/ssrn.4030341 · Cited by 112
Energy compaction-based image compression using convolutional autoencoder
Cheng, Z., Sun, H., Takeuchi, M., & Katto, J. (2020) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2019.2938345 · Cited by 97
Exploiting Prediction Error Inconsistencies through LSTM-based Classifiers to Detect Deepfake Videos
Amerini, I., & Caldelli, R. (2020) · Proceedings of the 2020 ACM Workshop on Information Hiding and Multimedia Security · doi:10.1145/3369412.3395070 · Cited by 64 · cited 1×
“In recent approaches, deep learning automatically extracts significant and discriminative characteristics to detect deepfakes [21, 22].”
BackgroundLarge-Scale Image Clustering Based on Camera Fingerprints
Lin, X., & Li, C.-T. (2016) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2016.2636086 · Cited by 46
Research works printed but not linked: 36
- Goodfellow I. J., 2014, Generative adversarial nets, “NIPS” 14, Proceedings of the 27th International Conference on Neural Information Processing Systems, 2, 2672
- 10.1109/tpami.2019.2903062 · DOI · Paper page
- De LimaO. FranklinS. BasuS. KarwoskiB. andGeorgeA. Deepfake detection using spatiotemporal convolutional networks 2020 https://arxiv.org/abs/2006.14749. · arXiv
- ParkhiO. M. VedaldiA. andZissermanA. Deep face recognition Proceedings of the British Machine Vision Conference (BMVC) September 2015 Swansea UK 41.1–41.12 https://doi.org/10.5244/c.29.41. · DOI · Paper page
- BrockA. DonahueJ. andSimonyanK. Large scale GAN training for high fidelity natural image synthesis 2018 https://arxiv.org/abs/1809.11096. · arXiv
- MiyatoT. KataokaT. KoyamaM. andYoshidaY. Spectral normalization for generative adversarial networks 2018 https://arxiv.org/abs/1802.05957. · arXiv
- AgarwalS.andVarshneyL. R. Limits of deep- fake detection: a robust estimation viewpoint 2019 https://arxiv.org/abs/1905.03493. · arXiv
- 10.1145/3072959.3073640 · DOI · Paper page
- KorshunovP.andMarcelS. Speaker inconsistency detection in tampered video Proceedings of the 26th European Signal Processing Conference (EUSIPCO) September 2018 Rome Italy 2375–2379 https://doi.org/10.23919/eusipco.2018.8553270 2-s2.0-85059800475. · DOI · Paper page
- GalballyJ.andMarcelS. Face anti-spoofing based on general image quality assessment Proceedings of the 22nd International Conference on Pattern Recognition August 2014 Stockholm Sweden 1173–1178 https://doi.org/10.1109/icpr.2014.211 2-s2.0-84919935868. · DOI · Paper page
- 10.1016/j.patcog.2017.07.001 · DOI
- 10.1016/j.eswa.2016.10.038 · DOI · Paper page
- 10.1007/s11042-015-2847-3 · DOI
- ChopraS. Learning a similarity metric discriminatively with application to face verification Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition September 2005 San Diego CA USA 539–546. · DOI · Paper page
- HuangG. LiuZ. Van Der MaatenL. andWeinbergerK. Q. Densely connected convolutional networks Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition July 2017 Honolulu HI USA 4700–4708. · DOI · Paper page
- ChoK. van MerrienboerB. GulcehreC. BahdanauD. BougaresF. SchwenkH. andBengioY. Learning phrase representations using RNN encoder–decoder for statistical machine translation Proceedings of the 2014 Conference on Empirical Methods in Natural Language Pro- Cessing (EMNLP) October 2014 Doha Qatar 1724–1734. · DOI · Paper page
- GueraD.andDelpE. J. Deepfake video detection using recurrent neural networks Proceedings of the 2018 15th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS) November 2018 Auckland New Zealand 1–6. · DOI · Paper page
- Sabour S., 2017, Advances in Neural Information Processing Systems, 3856
- ChingovskaI. AnjosA. andMarcelS. On the effectiveness of local binary patterns in face anti-spoofing Proceedings of the International Conference of Biometrics Special Interest Group (BIOSIG) September 2012 Darmstadt Germany 1–7.
- ThiesJ. ZollhoferM. StammingerM. TheobaltC. andNießnerM. Face2Face: real-time face capture and reenactment of RGB videos Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition June 2016 Las Vegas NV USA 2387–2395. · DOI · Paper page
- RahmouniN. NozickV. YamagishiJ. andEchizenI. Distinguishing computer graphics from natural images using convolution neural networks Proceedings of the 2017 IEEE Workshop on Information Forensics and Security (WIFS) December 2017 Rennes France 1–6. · DOI · Paper page
- KoopmanM. RodriguezA. M. andGeradtsZ. Detection of deepfake video manipulation Proceedings of the 20th Irish Machine Vision and Image Processing Conference (IMVIP) August 2018 Belfast Ireland 133–136.
- 10.1117/12.814705 · DOI · Paper page
- 10.1109/TCSVT.2011.2160750 · DOI
- 10.1109/tbiom.2019.2942395 · DOI · Paper page
- 10.1109/tifs.2018.2886929 · DOI
- 10.1007/978-1-4614-0757-7 · DOI
- 10.7551/mitpress/10451.001.0001 · DOI · Paper page
- GüeraD. WangY. BondiL. BestaginiP. TubaroS. andDelpE. J. A counter forensic method for CNN-based camera model identification Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops July 2017 Honolulu HI USA 1840–1847. · DOI · Paper page
- GüeraD. YarlagaddaS. K. BestaginiP. ZhuF. TubaroS. andDelpE. J. Reliability map estimation for cnn-based camera model attribution Proceedings of the IEEE Winter Conference on Applications of Computer Vision March 2018 Lake Tahoe NV USA. · DOI
- RaghavendraR. RajaK. B. VenkateshS. andBuschC. Transferable deep-cnn features for detecting digital and print-scanned morphed face images Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops July 2017 Honolulu HI USA 1822–1830 https://doi.org/10.1109/cvprw.2017.228 2-s2.0-85030244602. · DOI · Paper page
- RösslerA. Faceforensics: a large-scale video dataset for forgery detection in human faces 2018 https://arxiv.org/abs/1803.09179. · arXiv
- https://arxiv.org/abs/1608.06993. · arXiv
- Tai Do NhuI. N.andKimS. H. Forensics face detection from GANs using convolutional neural network 2018 1–8 https://arxiv.org/abs/1902.11153v2. · arXiv
- JunayedM. S. AcneNet-a deep CNN based classification approach for acne classes Proceedings of the 12th International Conference on Information & Communication Technology and System (ICTS) 2019 Surabaya Indonesia 203–208 https://doi.org/10.1109/icts.2019.8850935 2-s2.0-85073513639. · DOI
- 10.14569/ijacsa.2021.0120622 · DOI
Cited by
An improved dense cnn architecture for deepfake image detection
Patel, Y., Tanwar, S., Bhattacharya, P., Gupta, R., Alsuwian, T., Davidson, I. E., & Mazibuko, T. F. (2023) · IEEE Access · doi:10.1109/access.2023.3251417 · Cited by 196
“Recent approaches have suggested convolutional neural networks (CNN) as an effective fit for DF detection models [17].”
BackgroundDeep fake detection and classification using error-level analysis and deep learning
Rafique, R., Gantassi, R., Amin, R., Frnda, J., Mustapha, A., & Alshehri, A. H. (2023) · Scientific Reports · doi:10.1038/s41598-023-34629-3 · Cited by 155
A systematic literature review on the effectiveness of deepfake detection techniques
Stroebel, L., Llewellyn, M., Hartley, T., Ip, T. S., & Ahmed, M. (2023) · Journal of Cyber Security Technology · doi:10.1080/23742917.2023.2192888 · Cited by 66
Enhanced deepfake detection with densenet and cross-vit
Siddiqui, F., Yang, J., Xiao, S., & Fahad, M. (2025) · Expert Systems with Applications · doi:10.1016/j.eswa.2024.126150 · Cited by 62
(2025) · doi:10.1016/j.procs.2025.04.148 · Cited by 9
Metadata
- Authors
- Shad, H. S., Rizvee, M. M., Roza, N. T., Hoq, S. M. A., Monirujjaman Khan, M., Singh, A., Zaguia, A., & Bourouis, S.
- Venue
- Computational Intelligence and Neuroscience
- Publisher
- Wiley
- Published
- 2021-01
- Volume
- 2021
- Issue
- 1
- Pages
- 3111676-3111676
- ISSN
- 1687-5265 (ISSN-L)
- 1687-5273
- OpenAlex
- W4200434941
- Cited by
- 93
- References
- 25
- FWCI
- 5.47
- Type
- journal article
- Language
- en
- Status
- Retracted
- Update notices
- retraction (2023-11-29)
- Open access
- hybrid
- Funders
- Taif University (TURSP-2020/26)
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.