Automated face swapping and its detection
The DOI matches its Crossref record; 14 of the 14 references it cites were found in a registry or an index.
Abstract
Face has been used as one of the mainstream manners for user identification. However, with the popularity of face-swapping apps, it takes only a few seconds to change the faces between two facial images. Such swapped results, when using improperly or carelessly, might create some security issues in certain applications. This paper is the first work to address the importance of this issue and discusses the feasibility to achieve an automated face swapping detection through machine learning. Several approaches are tested on a face swapping database derived from a face benchmarking repository. The best solution in the experiments achieved a detection accuracy of over 92%.
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
“Recent works on adversarial perturbation attacks to fool DNN-based detectors make the deepfake detection task more difficult [157, 171–174].”
From Deep learning for deepfakes creation and detection: A survey (2022) · cites this paper as [174]
Citations
Cites
LIBSVM: A library for support vector machines
Chang, C.-C., & Lin, C.-J. (2011) · ACM Transactions on Intelligent Systems and Technology · doi:10.1145/1961189.1961199 · Cited by 40,918 · cited 12×
“Compared to current popular deep learning tools that require large dateset of hundred-thousands of images for training [20], SVM [17] is a lite tool that can be easily applied to the relatively small-scale task in this paper.”
BackgroundMethodInfluentialLabeled Faces in the Wild: A Database forStudying Face Recognition in Unconstrained Environments
Huang, G. B., Mattar, M., Berg, T. L., & Miller, E. G. (2008) · HAL · Cited by 4,822
Learning Face Representation from Scratch
Yi, D., Lei, Z., Liao, S., & Li, S. Z. (2014) · arXiv (Cornell University) · doi:10.48550/arxiv.1411.7923 · Cited by 1,521 · cited 1×
“Compared to current popular deep learning tools that require large dateset of hundred-thousands of images for training [20], SVM [17] is a lite tool that can be easily applied to the relatively small-scale task in this paper.”
MethodSplines minimizing rotation-invariant semi-norms in Sobolev spaces
Duchon, J. (1977) · Lecture Notes in Mathematics · doi:10.1007/bfb0086566 · Cited by 1,380 · cited 1×
“2) Align two faces using the detected landmarks based on the thin-plate spline model [14].”
MethodEnsemble Classifiers for Steganalysis of Digital Media
Kodovsky, J., Fridrich, J., & Holub, V. (2012) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2011.2175919 · Cited by 1,064 · cited 3×
“The RF takes the default setting in [18] and the hidden layer size of the MLP is set to 800.”
BackgroundMethodFace Spoof Detection With Image Distortion Analysis
Wen, D., Han, H., & Jain, A. K. (2015) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2015.2400395 · Cited by 905 · cited 1×
“Specifically, current falsifying data are fake copies of an authorized client's face, in forms such as photos or videos [5, 6].”
Background(2012) · Infoscience (Ecole Polytechnique Fédérale de Lausanne) · Cited by 826
A face antispoofing database with diverse attacks
Zhang, Z., Yan, J., Liu, S., Lei, Z., Yi, D., & Li, S. Z. (2012) · 2012 5th IAPR International Conference on Biometrics (ICB) · doi:10.1109/icb.2012.6199754 · Cited by 816 · cited 1×
“Specifically, current falsifying data are fake copies of an authorized client's face, in forms such as photos or videos [5, 6].”
BackgroundDiscriminant Analysis of Principal Components for Face Recognition
Zhao, W., Krishnaswamy, A., Chellappa, R., Swets, D. L., & Weng, J. (1998) · Face Recognition · doi:10.1007/978-3-642-72201-1_4 · Cited by 696
LBP − TOP Based Countermeasure against Face Spoofing Attacks
de Freitas Pereira, T., Anjos, A., De Martino, J. M., & Marcel, S. (2013) · Lecture Notes in Computer Science · doi:10.1007/978-3-642-37410-4_11 · Cited by 319
Research works printed but not linked: 7
- 0, Bian Lian
- 0, Face Swap Booth-photo faceswap & face changer
- 0, Auto Face Swap
- 0, Face Swap Live
- bay, 2006, Surf: Speeded up robust features[C], European Conference on Computer Vision, 404
- wen, 2015, Face spoof detection with image distortion analysis, Information Forensics and Security, IEEE Transactions on, 10, 746
- 0, Windows Hello face authentication
Cited by
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
“proposed a bag of words classifier [40], and Zhou et al.”
BackgroundMasood, M., Nawaz, M., Malik, K. M., Javed, A., Irtaza, A., & Malik, H. (2023) · Applied Intelligence · doi:10.1007/s10489-022-03766-z · Cited by 543
“Recently, some researchers [157, 187] have adopted the idea of employing the traditional methods of image forgery identification to deepfake detection.”
BackgroundMethodInfluentialFakeCatcher: Detection of Synthetic Portrait Videos using Biological Signals
Ciftci, U. A., Demir, I., & Yin, L. (2024) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2020.3009287 · Cited by 499
DeepFakes: a New Threat to Face Recognition? Assessment and Detection
Korshunov, P., & Marcel, S. (2018) · arXiv · doi:10.48550/arxiv.1812.08685 · Cited by 497
“For instance, Zhang et al. [20] proposed the method based on speeded up robust features (SURF) descriptors and SVM classifier.”
MethodDeep 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) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2022.103525 · Cited by 464
“[78] used the bag of words method to extract a set of compact features and fed it into various classifiers such as SVM [79], random forest (RF) [80] and multi-layer perceptrons (MLP) [81] for discriminating swapped face images from the genuine.”
MethodDeep 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. (2019) · arXiv · doi:10.48550/arxiv.1909.11573 · Cited by 464
“Zhang et al. [46] used the bag of words method to extract a set of compact features and fed it into various classifiers such as SVM [47], random forest (RF) [48] and multi-layer perceptrons (MLP) [49] for discriminating swapped face images from the genuine.”
MethodDeepFake 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
Countering 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
“Zhang et al. (2017) detect the key points in facial images and applied a descriptor to represent them for capturing the local information, then a linear classifier is applied for effective detection.”
MethodA survey on image tampering and its detection in real-world photos
Zheng, L., Zhang, Y., & Thing, V. L. L. (2019) · Journal of Visual Communication and Image Representation · doi:10.1016/j.jvcir.2018.12.022 · Cited by 174
Self-citationFake face detection via adaptive manipulation traces extraction network
Guo, Z., Yang, G., Chen, J., & Sun, X. (2021) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2021.103170 · Cited by 165
“[54] constructed a feature set of bag of words, which provides distinguishable features into SVM for binary classification.”
BackgroundVulnerability 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
“[25] proposed the method based on speeded up robust features (SURF) descriptors and SVM classifier.”
MethodA comprehensive overview of Deepfake: generation, detection, datasets, and opportunities
Seow, J. W., Lim, M. K., Phan, R. C. W., & Liu, J. K. (2022) · Neurocomputing · doi:10.1016/j.neucom.2022.09.135 · Cited by 149
A Survey on the Detection and Impacts of Deepfakes in Visual, Audio, and Textual Formats
Mubarak, R., Alsboui, T., Alshaikh, O., Inuwa-Dutse, I., Khan, S., & Parkinson, S. (2023) · IEEE Access · doi:10.1109/access.2023.3344653 · Cited by 132
Recent advances in digital image manipulation detection techniques: A brief review
Thakur, R., & Rohilla, R. (2020) · Forensic Science International · doi:10.1016/j.forsciint.2020.110311 · Cited by 125
Ciftci, U. A., Demir, I., & Yin, L. (2020) · 2020 IEEE International Joint Conference on Biometrics (IJCB) · doi:10.1109/ijcb48548.2020.9304909 · Cited by 115
“Spe-cific generative networks [12, 59, 29, 36, 71, 72, 50] have been applied as the discriminators.”
MethodDeep Learning for Deepfakes Creation and Detection: A Survey
Nguyen, T. T., Nguyen, M. C., Nguyen, D. T., Nguyen, D. T., & Nahavandi, S. (2020) · Figshare · doi:10.6084/m9.figshare.12731039.v1 · Cited by 121
Face Generation and Editing With StyleGAN: A Survey
Melnik, A., Miasayedzenkau, M., Makaravets, D., Pirshtuk, D., Akbulut, E., Holzmann, D., Renusch, T., Reichert, G., & Ritter, H. (2024) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2024.3350004 · Cited by 105
“Face replacement can be established using classical computer graphics-based approaches [101] by using facial landmarks extracted for each face.”
BackgroundRETRACTED ARTICLE: Deepfake detection using rationale-augmented convolutional neural network
Ahmed, S. R., & Sonuç, E. (2021) · Applied Nanoscience · doi:10.1007/s13204-021-02072-3 · Cited by 125
“In this paper (Zhang et al. 2017), the author returns a labeled matrix that consists of positive integer values for different regions and deepfake network for ridgelines.”
BackgroundRetractedShad, H. S., Rizvee, M. M., Roza, N. T., Hoq, S. M. A., Monirujjaman Khan, M., Singh, A., Zaguia, A., & Bourouis, S. (2021) · Computational Intelligence and Neuroscience · doi:10.1155/2021/3111676 · Cited by 93
“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.”
BackgroundRetractedDetecting fake images by identifying potential texture difference
Yang, J., Xiao, S., Li, A., Lan, G., & Wang, H. (2021) · Future Generation Computer Systems · doi:10.1016/j.future.2021.06.043 · Cited by 86
Where Do Deep Fakes Look? Synthetic Face Detection via Gaze Tracking
Demir, I., & Ciftci, U. A. (2021) · ACM Symposium on Eye Tracking Research and Applications · doi:10.1145/3448017.3457387 · Cited by 55
“The first family of detectors have limitations such as only processing images [Nguyen et al. 2019; Tariq et al. 2018; Zhang et al. 2017; Zhou et al. 2017] or audio [Korshunov and Marcel 2018], detecting the fakes of specific generators [Afchar et al. 2018; Khodabakhsh et al. 2018; Roy et al. 2018;…”
Swapped face detection using deep learning and subjective assessment
Ding, X., Raziei, Z., Larson, E. C., Olinick, E. V., Krueger, P., & Hahsler, M. (2020) · EURASIP Journal on Information Security · doi:10.1186/s13635-020-00109-8 · Cited by 71
“Zhang et al. [26] created swapped faces using labeled faces in the wild (LFW) dataset [13].”
BackgroundDeepfake 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
“The second replacement technique, swap, refers to the ability to digitally insert content from a source to a specified target while allowing the specified target to drive the change [23].”
BackgroundImage forgery detection: comprehensive review of digital forensics approaches
Singh, S. P., & Kumar, R. (2024) · Journal of Computational Social Science · doi:10.1007/s42001-024-00265-8 · Cited by 65
“This authentication method is popular in organizations for person identification and on personal devices such as mobile phones and personal computers [45].”
Improving Generalization of Deepfake Detection With Data Farming and Few-Shot Learning
Korshunov, P., & Marcel, S. (2022) · IEEE Transactions on Biometrics, Behavior, and Identity Science · doi:10.1109/tbiom.2022.3143404 · Cited by 50
“…networks, such as Xception [1], capsules networks [8], EfficientNet [2], and discriminators of GANs used to generate synthetic images [9], which were shown to outperform the methods based on shallow CNNs, facial physical characteristics [10], [11], [12], [13], or distortion features [14], [15].”
MethodDeepfakes Classification of Faces Using Convolutional Neural Networks
Sharma, J., Sharma, S., Kumar, V., Hussein, H. S., & Alshazly, H. A. (2022) · Traitement du signal · doi:10.18280/ts.390330 · Cited by 62
“FaceSwap [54] Swapme [55] [35] SVM, RF,MLP Extraction of discriminant features using a bag of words method.”
MethodResNet-Swish-Dense54: a deep learning approach for deepfakes detection
Nawaz, M., Javed, A., & Irtaza, A. (2022) · The Visual Computer · doi:10.1007/s00371-022-02732-7 · Cited by 55
“The method [20] works well for the manipulated images, however, lacks to generalize well to the video-based altered multimedia content.”
Method“Combating deepfakes: multi-LSTM and blockchain as proof of authenticity for digital media,”
Ki Chan, C. C., Kumar, V., Delaney, S., & Gochoo, M. (2020) · 2020 IEEE / ITU International Conference on Artificial Intelligence for Good (AI4G) · doi:10.1109/ai4g50087.2020.9311067 · Cited by 48
“In terms of deepfake image detection, one attempt to detect fabricated images used the bag of words method to extract a set of compact features and subsequently feeding it into SVM, random forest and multi-layer perceptrons in order to discern the real from the fake image [34].”
MethodUsing deepfakes for experiments in the social sciences - A pilot study
Eberl, A., Kühn, J., & Wolbring, T. (2022) · Frontiers in Sociology · doi:10.3389/fsoc.2022.907199 · Cited by 48
FFR_FD: Effective and fast detection of DeepFakes via feature point defects
Wang, G., Jiang, Q., Jin, X., & Cui, X. (2022) · Information Sciences · doi:10.1016/j.ins.2022.03.026 · Cited by 47
“In current largescale DeepFake datasets, to directly train the classifier with descriptors or BOWs [72] (constructed from descriptors by k-means) consumes much time and is prone to overfitting.”
BackgroundDeepfake Detection Using Spatiotemporal Transformer
Kaddar, B., Fezza, S. A., Akhtar, Z., Hamidouche, W., Hadid, A., & Serra-Sagrista, J. S. (2024) · ACM Transactions on Multimedia Computing Communications and Applications · doi:10.1145/3643030 · Cited by 72
“Zhang et al. [80] used the bag of words method to extract a set of compact features and exploited them as input for a binary classification algorithm to distinguish swapped face images from genuine images.”
Towards Multimodal Disinformation Detection by Vision-language Knowledge Interaction
Li, Q., Gao, M., Zhang, G., Zhai, W., Chen, J., & Jeon, G. (2023) · Information Fusion · doi:10.1016/j.inffus.2023.102037 · Cited by 64
A Comparative Evaluation of Local Feature Descriptors for DeepFakes Detection
Akhtar, Z., & Dasgupta, D. (2019) · 2019 IEEE International Symposium on Technologies for Homeland Security (HST) · doi:10.1109/hst47167.2019.9033005 · Cited by 42
“For instance, Zhang et al. [31] developed a technique based on bag of words to recognize samples with face substitutions.”
MethodImproving Deepfake Detection Generalization by Invariant Risk Minimization
Yin, Z., Wang, J., Xiao, Y., Zhao, H., Li, T., Zhou, W., Liu, A., & Liu, X. (2024) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2024.3355651 · Cited by 64
“Existing deepfake detection methods can be roughly divided into two categories, heuristic methods [8], [9], [10], [11], [12], [13], [14] and DNN-based methods [15], [16], [17], [18], [19], [20], [21], [22].”
BackgroundMethodExploring Adversarial Fake Images on Face Manifold
Li, D., Wang, W., Fan, H., & Dong, J. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr46437.2021.00573 · Cited by 43
Feature fusion Vision Transformers using MLP-Mixer for enhanced deepfake detection
Essa, E. (2024) · Neurocomputing · doi:10.1016/j.neucom.2024.128128 · Cited by 52
Visual Deepfake Detection: Review of Techniques, Tools, Limitations, and Future Prospects
Ur Rehman Ahmed, N., Badshah, A., Adeel, H., Tajammul, A., Daud, A., & Alsahfi, T. (2025) · IEEE Access · doi:10.1109/access.2024.3523288 · Cited by 45
Deep Insights of Deepfake Technology : A Review
Mahmud, B. U., & Sharmin, A. (2021) · arXiv · doi:10.48550/arxiv.2105.00192 · Cited by 38
“Zhang et al. [91] introduced a classifiers that used SVM,RF,MLP to extract discriminant features and classify real vs fabricated.”
MethodExploring deepfake technology: creation, consequences and countermeasures
Alanazi, S., & Asif, S. (2024) · Human-Intelligent Systems Integration · doi:10.1007/s42454-024-00054-8 · Cited by 75
Efficient deepfake detection using shallow vision transformer
Usmani, S., Kumar, S., & Sadhya, D. (2023) · Multimedia Tools and Applications · doi:10.1007/s11042-023-15910-z · Cited by 51
“The work proposed by Zhang et al. detects swapped faces from input images [31].”
InfluentialAuguring Fake Face Images Using Dual Input Convolution Neural Network
Bhandari, M., Neupane, A., Mallik, S., Gaur, L., & Qin, H. H. (2022) · Journal of Imaging · doi:10.3390/jimaging9010003 · Cited by 38
“[23] utilized the LFW face database [24] to extract a set of compact features using the bag of words approach and then fed those features into SVM, RF, and MLP classifiers to distinguish swapped-face photos from real ones, acheiving accuracies of 82.”
BackgroundMethodA comprehensive evaluation of feature-based AI techniques for deepfake detection
Sandotra, N., & Arora, B. (2024) · Neural Computing and Applications · doi:10.1007/s00521-023-09288-0 · Cited by 37
Subjective and Objective Evaluation of Deepfake Videos
Korshunov, P., & Marcel, S. (2021) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp39728.2021.9414258 · Cited by 44
“…and test detection approaches based on very deep neural networks, such as Xception [3], capsules networks [6], ResNet-50 [7], and EfficientNet [8], which were shown to outperform the methods based on shallow CNNs, facial physical characteristics [9, 10, 11], or distortion features [12, 13, 14].”
MethodFCD-Net: Learning to Detect Multiple Types of Homologous Deepfake Face Images
Han, R., Wang, X., Bai, N., Wang, Q., Liu, Z., & Xue, J. (2023) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2023.3269152 · Cited by 39
“Zhang et al. [13] proposed a method that extracts key points of image, uses the K-means method to generate BoW (Bag of Words) features, and then performs binary classification through SVM (Support Vector Machine) to judge authenticity.”
MethodA deep learning model for FaceSwap and face-reenactment deepfakes detection
Nawaz, M., Javed, A., & Irtaza, A. (2024) · Applied Soft Computing · doi:10.1016/j.asoc.2024.111854 · Cited by 40
Deepfake Image Detection using CNNs and Transfer Learning
Kumar, N., Pranav, P., Nirney, V., & Geetha, V. (2021) · International Conference on Computing, Communication and Green Engineering (CCGE) · doi:10.1109/ccge50943.2021.9776410 · Cited by 39
Masud, U., Sadiq, M., Masood, S., Ahmad, M., & El‐Latif, A. A. A. (2023) · Signal Image and Video Processing · doi:10.1007/s11760-023-02633-9 · Cited by 36
“[2] was one of the first papers that employed machine learning-based predictions like support vector machines (SVM), random forest classifiers (RF) and multilayer perceptrons (MLP).”
BackgroundImproving Generalization of Deepfake Detection by Training for Attribution
Jain, A., Korshunov, P., & Marcel, S. (2021) · IEEE International Workshop on Multimedia Signal Processing (MMSP) · doi:10.1109/mmsp53017.2021.9733468 · Cited by 36
“…researchers to train and test detection approaches based on very deep neural networks, such as Xcep-tion [16], capsules networks [14], and EfficientNet [13], which were shown to outperform the methods based on shallow CNNs, facial physical characteristics [1], [22], or distortion features [9], [24].”
MethodAhmed, S. R., & Sonuç, E. (2023) · Soft Computing · doi:10.1007/s00500-023-09245-y · Cited by 26
RetractedDeepfake Detection Based on the Adaptive Fusion of Spatial‐Frequency Features
Wang, F., Chen, Q., Jing, B., Tang, Y., Song, Z., & Wang, B. (2024) · International Journal of Intelligent Systems · doi:10.1155/2024/7578036 · Cited by 26
Liu, D., Chen, T., Peng, C., Wang, N., Hu, R., & Gao, X. (2024) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2024.3516561 · Cited by 29
“Early related works focus on designed hand-crafted features [3] to analyze the difference between real and fake images.”
BackgroundMethodInfluentialExposing DeepFake Videos Using Attention Based Convolutional LSTM Network
Su, Y., Xia, H., Liang, Q., & Nie, W. (2021) · Neural Processing Letters · doi:10.1007/s11063-021-10588-6 · Cited by 26
“Traditional DeepFaketechniqueusestwoautoencodersforparalleltraining,ofwhichtheoutputsare oftencombinedwithnotablefeaturesliketheresolutionchangesinthemanipulatingarea [15,48],theinconsistentoftheheadposemovements[11,41],andsoon.”
BackgroundImage quality assessment based fake face detection
Kiruthika, S. U., & Masilamani, V. (2022) · Multimedia Tools and Applications · doi:10.1007/s11042-021-11493-9 · Cited by 30
“Zhang et al. have proposed a support vector machine (SVM) based face detection model [50] by extracting the speeded up robust features (SURF) and fed into a bag of words.”
MethodDeepfake Video Detection via Facial Action Dependencies Estimation
Tan, L., Wang, Y., Wang, J., Yang, L., Chen, X., & Guo, Y. (2023) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v37i4.25658 · Cited by 40
“Early frame-level methods usually rely on the hand-crafted or statistical features (Fridrich and Kodovsky 2012; Zhang, Zheng, and Thing 2017).”
MethodDiscrepancy-Aware Meta-Learning for Zero-Shot Face Manipulation Detection
Yu, B., Li, X., Li, W., Zhou, J., & Lu, J. (2023) · IEEE Transactions on Image Processing · doi:10.1109/tip.2023.3289321 · Cited by 25
“Spatial-based methods aim to exploit the spatial artifacts generated in blending [5], [21], [49], [73], forensics [46], [69], [70] and environment [40].”
BackgroundDeepfake Detection Using XceptionNet
Ashok, V., & Joy, P. T. (2023) · IEEE International Conference on Recent Advances in Systems Science and Engineering (RASSE) · doi:10.1109/rasse60029.2023.10363477 · Cited by 23
“This issue was addressed in [15].”
Zhang, G., Gao, M., Li, Q., Zhai, W., & Jeon, G. (2024) · Cognitive Computation · doi:10.1007/s12559-024-10316-x · Cited by 26
Deepfakes in digital media forensics: Generation, AI-based detection and challenges
Bendiab, G., Haiouni, H., Moulas, I., & Shiaeles, S. N. (2024) · Journal of Information Security and Applications · doi:10.1016/j.jisa.2024.103935 · Cited by 35
Deepfakes Detection Methods: A Literature Survey
Weerawardana, M., & Fernando, T. (2021) · 2021 10th International Conference on Information and Automation for Sustainability (ICIAfS) · doi:10.1109/iciafs52090.2021.9606067 · Cited by 23
The Adversarial AI-Art: Understanding, Generation, Detection, and Benchmarking
Li, Y., Liu, Z., Zhao, J., Ren, L., Li, F., Luo, J., & Luo, B. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-70879-4_16 · Cited by 30
Artificial Intelligence and Applications
(2022) · doi:10.5121/csit.2022.1209 · Cited by 18
GAN-generated fake face detection via two-stream CNN with PRNU in the wild
Wang, J., Zeng, K., Ma, B., Luo, X., Yin, Q., Liu, G., & Jha, S. K. (2022) · Multimedia Tools and Applications · doi:10.1007/s11042-021-11592-7 · Cited by 19
“At present, many researchers have contributed their ideas in the detection of fake faces, some of which are based on traditional image forensics [19, 26, 28, 31], and some are based on deep learning [9, 20, 27, 36].”
BackgroundMethodCyber Vaccine for Deepfake Immunity
Chang, C., Nguyen, H. H., Yamagishi, J., & Echizen, I. (2023) · IEEE Access · doi:10.1109/access.2023.3311461 · Cited by 26
“For instance, the blending boundary may leave detectable imperfections [32], [33], [34], [35], [36].”
BackgroundEvaluation of Pre-Trained CNN Models for Geographic Fake Image Detection
Fezza, S. A., Ouis, M. Y., Kaddar, B., Hamidouche, W., & Hadid, A. (2022) · IEEE International Workshop on Multimedia Signal Processing (MMSP) · doi:10.1109/mmsp55362.2022.9949282 · Cited by 20
“[32] used the bag-of-words method to extract a set of discriminating features that were fed into various classifiers to discriminate manipulated face images”
MethodFake-checker: A fusion of texture features and deep learning for deepfakes detection
Huda, N. U., Javed, A., Maswadi, K., Alhazmi, A. H., & Ashraf, R. (2023) · Multimedia Tools and Applications · doi:10.1007/s11042-023-17586-x · Cited by 21
Multi-Feature Fusion Based Deepfake Face Forgery Video Detection
Lai, Z., Wang, Y., Feng, R., Hu, X., & Xu, H. C. (2022) · Systems · doi:10.3390/systems10020031 · Cited by 17
“[13] first proposed a classical machine learning method to detect face changing images.”
BackgroundOn the effectiveness of handcrafted features for deepfake video detection
Kaddar, B., Fezza, S. A., Hamidouche, W., Akhtar, Z., Hadid, A., Serra-Sagrista, J. S., Hernández-Cabronero, M., & Sanchez, V. (2023) · Journal of Electronic Imaging · doi:10.1117/1.jei.32.5.053033 · Cited by 16
“32 Zhang et al. 33 used the bag-of-words (BoW) method to extract a set of compact features, which is fed to various classifiers, such as support vector machines (SVM), 34 random forests (RF), 35 and multi-layer perceptrons (MLP), 36 for discriminating swapped face images from genuine ones.”
MethodFace Forgery Detection Based on the Improved Siamese Network
Wang, B., Li, Y., Wu, X., Ma, Y., Song, Z., & Wu, M.-K. (2022) · Security and Communication Networks · doi:10.1155/2022/5169873 · Cited by 16
“Some traditional manual features such as speeded up robust features (SURF) [7], photo response nonuniformity (PRNU) [8], local binary pattern (LBP) [9], image quality measures (IQM) [10], etc.”
BackgroundDeepfake source detection in a heart beat
Çiftçi, U. A., Demir, İ., & Yin, L. (2023) · The Visual Computer · doi:10.1007/s00371-023-02981-0 · Cited by 18
“These methods can be further categorized into generic ones that aim to detect universal artifacts in face swapping [56, 57], generative models [58], and DNN-based deepfakes [59].”
Deep Learning for Forgery Face Detection Using Fuzzy Fisher Capsule Dual Graph
Arunkumar, P. M., Sangeetha, Y., Raja, P. V., & Sangeetha, S. N. (2022) · Information Technology And Control · doi:10.5755/j01.itc.51.3.31510 · Cited by 14
Privacy-Preserved In-Cabin Monitoring System for Autonomous Vehicles
Mishra, A., Cha, J., & Kim, S. (2022) · Computational Intelligence and Neuroscience · doi:10.1155/2022/5389359 · Cited by 15
“Machine-learning-based face swapping was suggested in [39].”
HCI Based In-Cabin Monitoring System for Irregular Situations with Occupants Facial Anonymization
Mishra, A., Cha, J., & Kim, S. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-68452-5_40 · Cited by 12
Review on Deep Fake: A looming Technological Threat
Chowdhury, S. M. A. K., & Lubna, J. I. (2020) · International Conference on Computing, Communication and Networking Technologies (ICCCNT) · doi:10.1109/icccnt49239.2020.9225630 · Cited by 11
“[12] This swapped outcomes, when utilizing incorrectly will make safety problems in some applications.”
MethodFake Face Detection via Adaptive Residuals Extraction NetworkPreprint
Guo, Z., Yang, G., Chen, J., & Sun, X. (2020) · arXiv (Cornell University) · Cited by 10
Ha, Q.-A., Le, N. Q. T., Nguyen, T. T. T., Pham, T. T. T., Pham, B. A., & Le, N. Q. L. (2023) · International Journal of Human-Computer Interaction · doi:10.1080/10447318.2023.2188538 · Cited by 11
“This is due to face recognition technology, which uses photos taken by a digital camera or live data feeds to identify or verify an individual, by analyzing some unique and special features of face regions, then comparing them with target models (Zhang et al., 2017).”
MethodA comprehensive analysis of digital video forensics techniques and challenges
Sandhya, & Kashyap, A. (2023) · Iran Journal of Computer Science · doi:10.1007/s42044-023-00165-6 · Cited by 12
A Visual Computing Unified Application Using Deep Learning and Computer Vision Techniques
Sowmya, B. J., Meeradevi, M., Seema, S., Dayananda, P., Supreeth, S., Shruthi, G., & Rohith, S. (2024) · International Journal of Interactive Mobile Technologies (iJIM) · doi:10.3991/ijim.v18i01.42673 · Cited by 11
A Forensic Method for DeepFake Image based on Face Recognition
Wu, J., Feng, K., Chang, X., & Yang, T. (2020) · High Performance Computing and Cluster Technologies Conference (HPCCT) · doi:10.1145/3409501.3409544 · Cited by 14
“…of the standardized cross-correlation scores between the real image and the forged image, the differences are distinguished [12]; Zhang et al. [13] used the Bag-of-words method to extract 64-dimensional SURF (Speeded Up Robust Features) features of human faces and tested them with Support…”
MethodA Novel Dense-Swish-CNN With Bi-LSTM Framework for Image Deepfake Detection
Soundarya, B. C., & Gururaj, H. L. (2025) · IEEE Access · doi:10.1109/access.2025.3570761 · Cited by 12
“Zhang et al. developed a feature set using a bag of words, which offers distinct features for SVM-based binary classification [20].”
DeepFidelity: Perceptual Forgery Fidelity Assessment for Deepfake Detection
Peng, C., Guo, H., Liu, D., Wang, N., Hu, R., & Gao, X. (2025) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2025.3621207 · Cited by 14
Vulnerability of Automatic Identity Recognition to Audio-Visual Deepfakes
Korshunov, P., Chen, H., Garner, P. N., & Marcel, S. (2023) · IEEE International Joint Conference on Biometrics (IJCB) · doi:10.1109/ijcb57857.2023.10449189 · Cited by 13
“Methods for detecting visual fakes range from those based on simple visual or facial features [62, 60, 2, 37], binary classifiers trained on fake images [55, 17] and videos [50, 41, 40], to the methods that try to generalize to new deepfake methods or various post-processing blending techniques [3, 33, 29].”
MethodExploring the Advancements and Challenges of Deepfake Face-swap: A Survey
Bakar, S. A. R. B. S. A., Waseem, S., Omar, Z., & Bilalashfaqahmed (2026) · Multimedia Tools and Applications · doi:10.1007/s11042-026-21285-8 · Cited by 15
Faceswap Deepfakes Detection using Novel Multi-directional Hexadecimal Feature Descriptor
Ain, Q., Javed, A., & Malik, K. M. (2022) · International Bhurban Conference on Applied Sciences and Technology (IBCAST) · doi:10.1109/ibcast54850.2022.9990223 · Cited by 12
“Literature shows that existing techniques, especially local descriptors [17] are unable to detect face swapped deepfakes on unseen data [7] and GAN-generated videos [12].”
BackgroundMethodHow Do Deepfakes Move? Motion Magnification for Deepfake Source Detection
Demir, İ., & Çiftçi, U. A. (2024) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv57701.2024.00471 · Cited by 20
“Initial deepfake detection research focused on finding pixel-level artifacts directly from data, proposing “blind” detectors [11, 13, 16, 33, 34, 41, 47, 54, 65, 77, 78, 78].”
BackgroundDellys, H. N., Mokeddem, H., & Sliman, L. (2025) · AI · doi:10.3390/ai6040078 · Cited by 9
“Zhang et al. [40] developed a model to detect face-swapping manipulations using bag-of-words features and SVMs [41].”
The Threat of Deepfakes to Computer and Human Visions
Korshunov, P., & Marcel, S. (2022) · Advances in computer vision and pattern recognition · doi:10.1007/978-3-030-87664-7_5 · Cited by 11
Exploiting spatiotemporal inconsistencies to detect deepfake videos in the wild
Khedkar, A., Peshkar, A., Nagdive, A. S., Gaikwad, M. A., & Baudha, S. (2022) · International Conference on Emerging Trends in Engineering and Technology (ICETET) · doi:10.1109/icetet-sip-2254415.2022.9791719 · Cited by 12
Swapping Face Images Based on Augmented Facial Landmarks and Its Detection
Sadu, C., & Das, P. K. (2020) · IEEE Region 10 Conference (TENCON) · doi:10.1109/tencon50793.2020.9293884 · Cited by 9
“In [26], the authors utilized SURF and Bag of Words (BoW) instead of raw pixels for features extraction.”
MethodLeveraging High-Frequency Components for Deepfake Detection
Mejri, N., Papadopoulos, K., & Aouada, D. (2021) · IEEE International Workshop on Multimedia Signal Processing (MMSP) · doi:10.1109/mmsp53017.2021.9733606 · Cited by 11
“The work in [16] uses speeded up robust features (SURF) [17] and support vector machines (SVM) to discriminate between real and swapped faces.”
MethodFramework for Quantum‐Based Deepfake Video Detection (Without Audio)
Pandey, A., Rudra, B., & Krishnan, R. K. (2025) · International Journal of Intelligent Systems · doi:10.1155/int/3990069 · Cited by 7
“Zheng et al. [17] extracted compact features using the bag-of-words method and trained these features with various ML models and multi-layer perceptrons (MLPs) to diferentiate between fake and real images.”
StegaFFD: Privacy-preserving Face Forgery Detection via Fine-grained Steganographic Domain Lifting
Ma, G., Lin, X., Ma, H., Liu, A., Liu, Y., Tang, W., Yu, S. P., Kong, C., & Yu, Y. (2026) · Machine Intelligence Research · doi:10.1007/s11633-025-1612-y · Cited by 6
“Face forgery detection initially relied on image processing methods (e.g., copy-move, splicing, deletion) to extract inherent features and train machine learning classifiers, such as Speeded-Up Robust Features (SURF) [71] and Photo Response Non-Uniformity (PRNU) [72].”
Ain, Q. U., Javed, A., Malik, K. M., & Irtaza, A. (2024) · Multimedia Tools and Applications · doi:10.1007/s11042-024-20268-x · Cited by 10
“Zhang et al. [ 11] used SURF for feature extraction and trained these features using an SVM for face swap deepfake detection.”
Generalized Deepfake Detection Using Identity, Behavioral, and Geometric Signatures
Farooq, M. U., Khan, A. A., Haq, I. U., & Malik, K. M. (2025) · IEEE Transactions on Computational Social Systems · doi:10.1109/tcss.2025.3588348 · Cited by 14
“For example, Zhang et al. [7] employed speeded up robust features (SURF) descriptors for detecting face swap deepfakes, but their method is solely developed to detect deepfake images and is ineffective when confronted with videos.”
Usharani, B. (2021) · Deep Fakes, Fake News, and Misinformation in Online Teaching and Learning Technologies · doi:10.4018/978-1-7998-6474-5.ch009 · Cited by 2
Deepfake Images, Videos Generation, and Detection Techniques Using Deep Learning
Singh, R., Shrivastava, S., Jatain, A., & Bajaj, S. B. (2022) · Algorithms for intelligent systems · doi:10.1007/978-981-16-9650-3_39 · Cited by 5
Real-Time Face Swapping System using OpenCV
Datta, A., Yadav, O. K., Singh, Y., Sountharrajan, S., Karthiga, M., & Suganya, E. (2021) · International Conference on Inventive Research in Computing Applications (ICIRCA) · doi:10.1109/icirca51532.2021.9545010 · Cited by 5
A Survey of Deep Fake Detection for Trial Courts
Celebi, N., Liu, Q., & Karatoprak, M. (2022) · doi:10.5121/csit.2022.120919 · Cited by 7
“[12] generated swapped faces using identified faces in the LFW dataset [13].”
MethodSadman, N., Hasan, K. A., Rashno, E., Alaca, F., Tian, Y., & Zulkernine, F. H. (2023) · IEEE Symposium Series on Computational Intelligence (SSCI) · doi:10.1109/ssci52147.2023.10371801 · Cited by 6
“In this research, we evaluate a popular open-source face recognition system called InsightFace against three blackbox attacks on InsightFace 1 : face swap [15], morphing [16], and presentation [17], because of their prevalence in the literature.”
MethodMelouk, M. M., Shao, M., Basit, A., Abouzahir, C., Zhou, R., & Shafique, M. (2025) · IEEE Access · doi:10.1109/access.2025.3614455 · Cited by 9
“Early approaches exploited physical inconsistencies—such as facial discrepancies, face-swapping artifacts [54], user stream descriptors [55], and irregular eye-blinking patterns [27]—but as handcrafted features proved inadequate, deep learning techniques emerged to harness spatial and temporal cues.”
Deep Learning based Model for Deepfake Image Detection: An Analytical Approach
Neha, & Arora, B. (2023) · International Conference on Innovative Mechanisms for Industry Applications · doi:10.1109/icimia60377.2023.10426561 · Cited by 6
“To differentiate real and face swap images, [36] employed the bag of words method to extract a set of compact features that were then fed into a variety of classifiers, including SVM, RF, and MLP.”
Method
Metadata
- Authors
- Zhang, Y., Zheng, L., & Thing, V. L. L.
- Affiliations
- Institute for Infocomm Research (SG)
- Venue
- 2017 IEEE 2nd International Conference on Signal and Image Processing (ICSIP)
- Publisher
- IEEE
- Published
- 2017-08
- Pages
- 15-19
- OpenAlex
- W2774037436
- Cited by
- 154
- References
- 14
- Citations by year
- 2026: 5 · 2025: 27 · 2024: 26 · 2023: 26 · 2022: 30 · 2021: 19 · 2020: 13 · 2019: 4 · 2018: 4
- FWCI
- 1.68
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- IEEE International Conference on Signal and Image Processing (ICSIP) (publishedVersion)
- Funders
- National Research Foundation Singapore
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Digital Media Forensic Detection
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Face recognition and analysis
- Physical Sciences › Computer Science › Signal Processing › Biometric Identification and Security
- Keywords
- face swapping, deepfake detection, machine learning detection
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.