Comparison of Deepfake Detection Techniques through Deep Learning
Open accessThe DOI matches its Crossref record; 23 of the 23 references it cites were found in a registry or an index.
Abstract
Deepfakes are realistic-looking fake media generated by deep-learning algorithms that iterate through large datasets until they have learned how to solve the given problem (i.e., swap faces or objects in video and digital content). The massive generation of such content and modification technologies is rapidly affecting the quality of public discourse and the safeguarding of human rights. Deepfakes are being widely used as a malicious source of misinformation in court that seek to sway a court’s decision. Because digital evidence is critical to the outcome of many legal cases, detecting deepfake media is extremely important and in high demand in digital forensics. As such, it is important to identify and build a classifier that can accurately distinguish between authentic and disguised media, especially in facial-recognition systems as it can be used in identity protection too. In this work, we compare the most common, state-of-the-art face-detection classifiers such as Custom CNN, VGG19, and DenseNet-121 using an augmented real and fake face-detection dataset. Data augmentation is used to boost performance and reduce computational resources. Our preliminary results indicate that VGG19 has the best performance and highest accuracy of 95% when compared with other analyzed models.
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
EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks
Tan, M., & Le, Q. V. (2019) · arXiv · doi:10.48550/arxiv.1905.11946 · Cited by 17,072 · cited 2×
“Other techniques that leverage spatial features and spatio-temporal anomalies in the supervised domain such as Xception [48] and EfficientNet [49] have been shown to be more efficient than CNNs.”
MethodFaceForensics++: 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
MesoNet: 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
Celeb-DF: A Large-Scale Challenging Dataset for DeepFake Forensics
Li, Y., Yang, X., Sun, P., Qi, H., & Lyu, S. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.00327 · Cited by 1,846 · cited 2×
“Considering the quality and quantity of the generated data, DFD, DeeperForensics, DFDC, and the Celeb-DF datasets are categorized as the second generation [25].”
MethodFace X-Ray for More General Face Forgery Detection
Li, L., Bao, J., Zhang, T., Yang, H., Chen, D., Wen, F., & Guo, B. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.00505 · Cited by 1,211
CNN-Generated Images Are Surprisingly Easy to Spot… for Now
Wang, S.-Y., Wang, O., Zhang, R., Owens, A., & Efros, A. A. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.00872 · Cited by 1,210
Exposing Deep Fakes Using Inconsistent Head Poses
Yang, X., Li, Y., & Lyu, S. (2019) · ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) · doi:10.1109/icassp.2019.8683164 · Cited by 1,196
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
Multi-attentional Deepfake Detection
Zhao, H., Wei, T., Zhou, W., Zhang, W., Chen, D., & Yu, N. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr46437.2021.00222 · Cited by 1,019 · cited 2×
“[10] proposed a multi-attentional deepfake detection network that can achieve a 97% accuracy by implementing multiple spatial attention heads, textural feature enhancement blocks and aggregating low-level textural features and high-level semantic features.”
BackgroundMethodCapsule-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
Exploiting Visual Artifacts to Expose Deepfakes and Face Manipulations
Matern, F., Riess, C., & Stamminger, M. (2019) · 2019 IEEE Winter Applications of Computer Vision Workshops (WACVW) · doi:10.1109/wacvw.2019.00020 · Cited by 824
DeeperForensics-1.0: A Large-Scale Dataset for Real-World Face Forgery Detection
Jiang, L., Li, R., Wu, W., Qian, C., & Loy, C. C. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.00296 · Cited by 599
Deepfake Video Detection through Optical Flow Based CNN
Amerini, I., Galteri, L., Caldelli, R., & Del Bimbo, A. (2019) · 2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW) · doi:10.1109/iccvw.2019.00152 · Cited by 424 · cited 1×
“VGG-19, even though it was great in terms of performance, aligns with results from [60]; it was computationally very expensive, especially if fed with augmented data.”
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×
“The work of [44,45] illustrated that eye pupils’ inconsistencies are one of the indicators of fake media.”
BackgroundDeep 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
Combining EfficientNet and Vision Transformers for Video Deepfake Detection
Coccomini, D. A., Messina, N., Gennaro, C., & Falchi, F. (2022) · Lecture Notes in Computer Science · doi:10.1007/978-3-031-06433-3_19 · Cited by 296 · cited 1×
“The main difference between deepfake video- and image-detection methods is that video-detection methods can leverage spatial features [14], spatio-temporal anomalies [15] and supervised domain [16] to draw a conclusion on the whole video by aggregating the inferred output both in time and across multiple faces.”
BackgroundA Survey on Deepfake Video Detection
Yu, P., Xia, Z., Fei, J., & Lu, Y. (2021) · IET Biometrics · doi:10.1049/bme2.12031 · Cited by 253
(2020) · doi:10.1007/978-3-030-68821-9_38 · Cited by 113
Detecting Deepfakes with Metric Learning
Kumar, A., Bhavsar, A., & Verma, R. (2020) · 2020 8th International Workshop on Biometrics and Forensics (IWBF) · doi:10.1109/iwbf49977.2020.9107962 · Cited by 90 · cited 3×
“The main difference between deepfake video- and image-detection methods is that video-detection methods can leverage spatial features [14], spatio-temporal anomalies [15] and supervised domain [16] to draw a conclusion on the whole video by aggregating the inferred output both in time and across multiple faces.”
BackgroundMethods of deepfake detection based on machine learning
Maksutov, A. A., Morozov, V. O., Lavrenov, A. A., & Smirnov, A. S. (2020) · 2020 IEEE Conference of Russian Young Researchers in Electrical and Electronic Engineering (EIConRus) · doi:10.1109/eiconrus49466.2020.9039057 · Cited by 74 · cited 1×
“Feature-based or attention-based matching techniques, however, are used for both deepfake video and image identification, and split the whole face into different regions of focus such as eye, nose, lips, skin, head position, color mismatches, etc. [32].”
MethodDeepfake forensics analysis: An explainable hierarchical ensemble of weakly supervised models
Silva, S. H., Bethany, M., Votto, A. M., Scarff, I. H., Beebe, N., & Najafirad, P. (2022) · Forensic Science International: Synergy · doi:10.1016/j.fsisyn.2022.100217 · Cited by 66 · cited 4×
“[12] were able to achieve a 92% accuracy on the DFDC dataset by implementing a hierarchical explainable forensics algorithm that”
BackgroundMethodInfluentialVideo Face Manipulation Detection Through Ensemble of CNNs
Bonettini, N., Cannas, E. D., Mandelli, S., Bondi, L., Bestagini, P., & Tubaro, S. (2021) · 2020 25th International Conference on Pattern Recognition (ICPR) · doi:10.1109/icpr48806.2021.9412711 · Cited by 27
Research works printed but not linked: 36
- Ferreira, S., Antunes, M., and Correia, M.E. (2021). Exposing Manipulated Photos and Videos in Digital Forensics Analysis. J. Imaging, 7. · DOI
- Goodfellow, I., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A., and Bengio, Y. (2021, November 28). Generative adversarial nets. Adv. Neural Inf. Process. Syst., Available online: https://proceedings.neurips.cc/paper/2014/hash/5ca3e9b122f61f8f06494c97b1afccf3-Abstract.html.
- Sajjadi, M.S., Scholkopf, B., and Hirsch, M. (2017, January 22–29). Enhancenet: Single image super-resolution through automated texture synthesis. Proceedings of the IEEE International Conference on Computer Vision, Venice, Italy. · DOI · Paper page
- Ferreira, S., Antunes, M., and Correia, M.E. (2021). A Dataset of Photos and Videos for Digital Forensics Analysis Using Machine Learning Processing. Data, 6. · DOI
- Durall, R., Keuper, M., Pfreundt, F.J., and Keuper, J. (2019). Unmasking deepfakes with simple features. arXiv.
- Roets, 2017, ‘Fake news’: Incorrect, but hard to correct. The role of cognitive ability on the impact of false information on social impressions, Intelligence, 65, 107, 10.1016/j.intell.2017.10.005 · DOI · Paper page
- Ismail, 2021, Deepfake video detection: YOLO-Face convolution recurrent approach, Peerj Comput. Sci., 7, e730, 10.7717/peerj-cs.730 · DOI
- Li, Y., and Lyu, S. (2018). Exposing deepfake videos by detecting face warping artifacts. arXiv.
- Korshunov, P., and Marcel, S. (2018). Deepfakes: A new threat to face recognition? assessment and detection. arXiv.
- Dolhansky, B., Bitton, J., Pflaum, B., Lu, J., Howes, R., Wang, M., and Ferrer, C.C. (2020). The DeepFake Detection Challenge Dataset. arXiv.
- Nguyen, T.T., Nguyen, C.M., Nguyen, D.T., Nguyen, D.T., and Nahavandi, S. (2019). Deep learning for deepfakes creation and detection: A survey. arXiv.
- Huang, Y., Juefei-Xu, F., Guo, Q., Xie, X., Ma, L., Miao, W., Liu, Y., and Pu, G. (2020). FakeRetouch: Evading deepfakes detection via the guidance of deliberate noise. arXiv.
- Zhao, 2003, Face recognition: A literature survey, Acm Comput. Surv. (CSUR), 35, 399, 10.1145/954339.954342 · DOI · Paper page
- Tariq, S., Lee, S., Kim, H., Shin, Y., and Woo, S.S. (2019, January 8–12). Gan is a friend or foe? a framework to detect various fake face images. Proceedings of the 34th ACM/SIGAPP Symposium on Applied Computing, Limassol, Cyprus. · DOI · Paper page
- Cozzolino, D., Thies, J., Rössler, A., Riess, C., Nießner, M., and Verdoliva, L. (2018). Forensictransfer: Weakly-supervised domain adaptation for forgery detection. arXiv.
- Simonyan, K., and Zisserman, A. (2014). Very deep convolutional networks for large-scale image recognition. arXiv.
- Chang, X., Wu, J., Yang, T., and Feng, G. (2020, January 27–30). Deepfake face image detection based on improved VGG convolutional neural network. Proceedings of the 2020 39th Chinese Control Conference (CCC), Shenyang, China. · DOI · Paper page
- Kim, J., Han, S., and Woo, S.S. (2019, January 9–12). Classifying Genuine Face images from Disguised Face Images. Proceedings of the 2019 IEEE International Conference on Big Data (Big Data), Los Angelas, CA, USA. · DOI
- Huang, G., Liu, Z., Van Der Maaten, L., and Weinberger, K.Q. (2017, January 21–26). Densely connected convolutional networks. Proceedings of the IEEE Conference on Computer Vision and Pattern recognition (CVPR), Honolulu, HI, USA. · DOI · Paper page
- Li, Y., Chang, M.C., and Lyu, S. (2018, January 11–13). In ictu oculi: Exposing ai created fake videos by detecting eye blinking. Proceedings of the 2018 IEEE International Workshop on Information Forensics and Security (WIFS 2018), Hong Kong, China. · DOI · Paper page
- Korshunov, P., and Marcel, S. (2018, January 3–7). Speaker inconsistency detection in tampered video. Proceedings of the 2018 26th European Signal Processing Conference (EUSIPCO), Rome, Italy. · DOI · Paper page
- Agarwal, S., Farid, H., Gu, Y., He, M., Nagano, K., and Li, H. (2019, January 16–20). Protecting World Leaders Against Deep Fakes. Proceedings of the CVPR Workshops, Long Beach, CA, USA.
- Chollet, F. (2017, January 21–26). Xception: Deep learning with depthwise separable convolutions. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, (CVPR), Honolulu, HI, USA. · DOI · Paper page
- Li, X., Yu, K., Ji, S., Wang, Y., Wu, C., and Xue, H. Fighting against deepfake: Patch&pair convolutional neural networks (PPCNN). Proceedings of the Companion Proceedings of the Web Conference, Taipei, Taiwan, 20–24 April 2020. · DOI · Paper page
- Pokroy, A.A., and Egorov, A.D. (2021, January 26–29). EfficientNets for deepfake detection: Comparison of pretrained models. Proceedings of the 2021 IEEE Conference of Russian Young Researchers in Electrical and Electronic Engineering (EIConRus), St. Petersburg, Russia. · DOI
- Mitra, A., Mohanty, S.P., Corcoran, P., and Kougianos, E. (2020, January 14–16). A novel machine learning based method for deepfake video detection in social media. Proceedings of the 2020 IEEE International Symposium on Smart Electronic Systems (iSES) (Formerly iNiS), Chennai, India. · DOI · Paper page
- Dolecki, M., Karczmarek, P., Kiersztyn, A., and Pedrycz, W. (2016, January 6–9). Utility functions as aggregation functions in face recognition. Proceedings of the 2016 IEEE Symposium Series on Computational Intelligence (SSCI), Athens, Greece. · DOI
- Du, C.X.T., Duong, L.H., Trung, H.T., Tam, P.M., Hung, N.Q.V., and Jo, J. (2020, January 1–4). Efficient-frequency: A hybrid visual forensic framework for facial forgery detection. Proceedings of the 2020 IEEE Symposium Series on Computational Intelligence (IEEE SSCI), Canberra, Australia. · DOI
- Tjon, E., Moh, M., and Moh, T.S. (2021, January 4–6). Eff-YNet: A Dual Task Network for DeepFake Detection and Segmentation. Proceedings of the 2021 15th International Conference on Ubiquitous Information Management and Communication (IMCOM), Seoul, Korea. · DOI
- Do, N.T., Na, I.S., and Kim, S.H. (2018, January 24–27). Forensics face detection from GANs using convolutional neural network. Proceedings of the 2018 International Symposium on Information Technology Convergence (ISITC 2018), Jeonju, Korea.
- Goel, R., Mehmood, I., and Ugail, H. (2021). A Study of Deep Learning-Based Face Recognition Models for Sibling Identification. Sensors, 21. · DOI
- Varoquaux, 2015, Scikit-learn: Machine learning without learning the machinery, Getmobile: Mob. Comput. Commun., 19, 29, 10.1145/2786984.2786995 · DOI · Paper page
- Son, S.B., Park, S.H., and Lee, Y.K. (2021, January 20–22). A Measurement Study on Gray Channel-based Deepfake Detection. Proceedings of the 2021 International Conference on Information and Communication Technology Convergence (ICTC), Jeju Island, Korea. · DOI
- Li, Y., Yang, X., Wu, B., and Lyu, S. (2019). Hiding faces in plain sight: Disrupting ai face synthesis with adversarial perturbations. arXiv.
- Corcoran, 2021, Countermeasure against Deepfake Using Steganography and Facial Detection, J. Comput. Commun., 9, 120, 10.4236/jcc.2021.99009 · DOI
- Guo, 2017, Fuzzy sparse autoencoder framework for single image per person face recognition, IEEE Trans. Cybern., 48, 2402, 10.1109/TCYB.2017.2739338 · DOI · Paper page
Cited by
Deepfake detection using convolutional vision transformers and convolutional neural networks
Soudy, A. H., Sayed, O., Tag-Elser, H., Ragab, R., Mohsen, S., Mostafa, T., Abohany, A. A., & Slim, S. O. (2024) · Neural Computing and Applications · doi:10.1007/s00521-024-10181-7 · Cited by 129
“As the use of deepfakes continues to increase, there is a need for effective methods of deepfake detection to protect society as a whole [27].”
Qureshi, S. M., Saeed, A., Almotiri, S. H., Ahmad, F., & Al Ghamdi, M. A. (2024) · PeerJ Computer Science · doi:10.7717/peerj-cs.2037 · Cited by 71
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
DeepFake Videos Detection Using Crowd Computing
Salini, Y., & HariKiran, J. (2024) · International Journal of Information Technology · doi:10.1007/s41870-023-01494-2 · Cited by 13
Xu, S., Yang, X., & Xie, Z. (2025) · Peer-to-Peer Networking and Applications · doi:10.1007/s12083-025-02048-y · Cited by 2
Metadata
- Authors
- Taeb, M., & Chi, H.
- Venue
- Journal of Cybersecurity and Privacy
- Publisher
- MDPI AG
- Published
- 2022-03-04
- Volume
- 2
- Issue
- 1
- Pages
- 89-106
- ISSN
- 2624-800X (ISSN-L)
- OpenAlex
- W4220982360
- Cited by
- 109
- References
- 23
- FWCI
- 6.72
- Type
- journal article
- Language
- en
- Open access
- gold
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.