GANprintR: Improved Fakes and Evaluation of the State of the Art in Face Manipulation Detection
Open accessThe DOI matches its Crossref record; 54 of the 54 references it cites were found in a registry or an index.
Abstract
The availability of large-scale facial databases, together with the remarkable progresses of deep learning technologies, in particular Generative Adversarial Networks (GANs), have led to the generation of extremely realistic fake facial content, raising obvious concerns about the potential for misuse. Such concerns have fostered the research on manipulation detection methods that, contrary to humans, have already achieved astonishing results in various scenarios. In this study, we focus on the synthesis of entire facial images, which is a specific type of facial manipulation. The main contributions of this study are four-fold: i) a novel strategy to remove GAN “fingerprints” from synthetic fake images based on autoencoders is described, in order to spoof facial manipulation detection systems while keeping the visual quality of the resulting images; ii) an in-depth analysis of the recent literature in facial manipulation detection; iii) a complete experimental assessment of this type of facial manipulation, considering the state-of-the-art fake detection systems (based on holistic deep networks, steganalysis, and local artifacts), remarking how challenging is this task in unconstrained scenarios; and finally iv) we announce a novel public database, named iFakeFaceDB, yielding from the application of our proposed GAN-fingerprint Removal approach (GANprintR) to already very realistic synthetic fake images. The results obtained in our empirical evaluation show that additional efforts are required to develop robust facial manipulation detection systems against unseen conditions and spoof techniques, such as the one proposed in this study.
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.
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?
The cited source doesn’t support the claim as written.
In the citing paper
“Neves et al. [35] implemented five methods on the Celeb-DF v2 dataset using the concept of a spatiotemporal convolutional network to detect DeepFake videos.”
From A Comprehensive Review of DeepFake Detection Using Advanced Machine Learning and Fusion Methods (2023) · cites this paper as [35]
Checked by a reasoning model — may be wrong.
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“iFakeFaceDB (Neves et al. 2020) is a fake image dataset for the study of synthetic face manipulation detection. It contains about 87,000 synthetic face images generated by the StyleGAN model (Karras et al. 2019) and transformed with the GANprintR (Neves et al. 2020) approach.”
From Countering Malicious DeepFakes: Survey, Battleground, and Horizon (2022) · cites this paper as Neves et al. 2020
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Besides, Neves et al. (2020) remove the 'fingerprints' in the fake faces through a pretrained GAN model, which can spoof the DeepFake detectors while maintaining the visual quality of the fake faces.”
From Countering Malicious DeepFakes: Survey, Battleground, and Horizon (2022) · cites this paper as Neves et al. 2020
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“iFakeFaceDB (Neves et al., 2020): This dataset includes 87,000 224 × 224 face images, generated by processing some StyleGAN-generated synthetic images using the GAN-fingerprint Removal approach (GANprintR) proposed by Neves et al. (2020).”
From Deepfake: definitions, performance metrics and standards, datasets, and a meta-review (2024) · cites this paper as Neves et al., 2020
Experimental — accuracy not yet measured
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
ImageNet: A large-scale hierarchical image database
Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., & Fei-Fei, L. (2009) · 2009 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2009.5206848 · Cited by 65,333 · cited 1×
“approach considered in [27]: i) the model was initialized with the weights obtained after training with the ImageNet dataset [46], ii) we changed the last fully-connected layer of the ImageNet”
MethodUnpaired image-to-image translation using cycle-consistent adversarial networks
Zhu, J.-Y., Park, T., Isola, P., & Efros, A. A. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.244 · Cited by 23,602 · cited 1×
“evaluated in [12] the robustness of different fake detectors over different training and testing scenarios, considering fake images created using image-to-image translations [49].”
BackgroundXception: 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
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
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 · cited 1×
“Their proposed approach, named FakeSpoter, extracted as features neuron coverage behaviors of real and fake faces from deep face recognition systems (i.e., VGG-Face [20], OpenFace [21], and FaceNet [22]), and then trained a SVM for the final classification.”
MethodA 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
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
Parkhi, O. M., Vedaldi, A., & Zisserman, A. (2015) · Procedings of the British Machine Vision Conference 2015 · doi:10.5244/c.29.41 · Cited by 5,479
Progressive Growing of GANs for Improved Quality, Stability, and Variation
Karras, T., Aila, T., Laine, S., & Lehtinen, J. (2017) · arXiv · doi:10.48550/arxiv.1710.10196 · Cited by 4,727
Spectral Normalization for Generative Adversarial Networks
Miyato, T., Kataoka, T., Koyama, M., & Yoshida, Y. (2018) · arXiv · doi:10.48550/arxiv.1802.05957 · Cited by 3,438
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 4×
“The effect of image resolution has been preliminary analysed in previous studies [27], [48], but for different facial manipulation groups, i.e., face swapping/identity swap and facial expression manipulation.”
BackgroundMethodResultInfluentialVGGFace2: A Dataset for Recognising Faces across Pose and Age
Cao, Q., Shen, L., Xie, W., Parkhi, O. M., & Zisserman, A. (2018) · 2018 13th IEEE International Conference on Automatic Face & Gesture Recognition (FG 2018) · doi:10.1109/fg.2018.00020 · Cited by 3,032
One millisecond face alignment with an ensemble of regression trees
Kazemi, V., & Sullivan, J. (2014) · 2014 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2014.241 · Cited by 2,831
MS-Celeb-1M: A Dataset and Benchmark for Large-Scale Face Recognition
Guo, Y., Zhang, L., Hu, Y., He, X., & Gao, J. (2016) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-46487-9_6 · Cited by 2,122 · cited 1×
“images from the MS-Celeb dataset [47], since it is disjoint from the datasets used in the development and evaluation of all the”
MethodLearning 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
Deepfakes 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
Self-citationExposing 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
Interpreting the Latent Space of GANs for Semantic Face Editing
Shen, Y., Gu, J., Tang, X., & Zhou, B. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.00926 · Cited by 1,063
Media Forensics and DeepFakes: An Overview
Verdoliva, L. (2020) · IEEE Journal of Selected Topics in Signal Processing · doi:10.1109/jstsp.2020.3002101 · Cited by 979 · cited 1×
“The most popular methods to generate fake face content can be categorised into four groups, regarding the level of manipulation [7], [8], [9]: i) entire face synthesis, ii) identity swap, iii) attribute manipulation, and iv) expression swap.”
Method(2016) · Cited by 844
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
Learning Rich Features for Image Manipulation Detection
Zhou, P., Han, X., Morariu, V. I., & Davis, L. S. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00116 · Cited by 778
On the Detection of Digital Face Manipulation
Dang, H., Liu, F., Stehouwer, J., Liu, X., & Jain, A. K. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.00582 · Cited by 764
Detecting and Simulating Artifacts in GAN Fake Images
Zhang, X., Karaman, S., & Chang, S.-F. (2019) · 2019 IEEE International Workshop on Information Forensics and Security (WIFS) · doi:10.1109/wifs47025.2019.9035107 · Cited by 567 · cited 1×
“Finally, we also include for completeness some relevant references to other recent studies focused on the detection of general GAN-based image manipulations, not facial ones: [12], [35]–[38].”
BackgroundDeepFakes: a New Threat to Face Recognition? Assessment and Detection
Korshunov, P., & Marcel, S. (2018) · arXiv · doi:10.48550/arxiv.1812.08685 · Cited by 497 · cited 1×
“The effect of image resolution has been preliminary analysed in previous studies [27], [48], but for”
ResultFighting Fake News: Image Splice Detection via Learned Self-Consistency
Huh, M., Liu, A., Owens, A., & Efros, A. A. (2018) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-01252-6_7 · Cited by 442
Biometric Antispoofing Methods: A Survey in Face Recognition
Galbally, J., Marcel, S., & Fierrez, J. (2014) · IEEE Access · doi:10.1109/access.2014.2381273 · Cited by 440
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
The Deepfake Detection Challenge (DFDC) Preview Dataset
Dolhansky, B., Howes, R., Pflaum, B., Baram, N., & Ferrer, C. C. (2019) · arXiv · doi:10.48550/arxiv.1910.08854 · Cited by 413 · cited 1×
“1) XceptionNet [44]: this network was selected, essentially because it provides the best detection results in the most recently published studies [9], [27], [45].”
ResultDetection of GAN-Generated Fake Images over Social Networks
Marra, F., Gragnaniello, D., Cozzolino, D., & Verdoliva, L. (2018) · 2018 IEEE Conference on Multimedia Information Processing and Retrieval (MIPR) · doi:10.1109/mipr.2018.00084 · Cited by 399 · cited 2×
“Finally, we also include for completeness some relevant references to other recent studies focused on the detection of general GAN-based image manipulations, not facial ones: [12], [35]–[38].”
BackgroundDo GANs leave artificial fingerprints?
Marra, F., Gragnaniello, D., Verdoliva, L., & Poggi, G. (2019) · 2019 IEEE Conference on Multimedia Information Processing and Retrieval (MIPR) · doi:10.1109/mipr.2019.00103 · Cited by 361
Detecting GAN generated Fake Images using Co-occurrence Matrices
Nataraj, L., Mohammed, T. M., Manjunath, B. S., Chandrasekaran, S., Flenner, A., Bappy, J. H., & Roy-Chowdhury, A. K. (2019) · Electronic Imaging · doi:10.2352/issn.2470-1173.2019.5.mwsf-532 · Cited by 331
FakeSpotter: A Simple yet Robust Baseline for Spotting AI-Synthesized Fake Faces
Wang, R., Juefei-Xu, F., Ma, L., Xie, X., Huang, Y., Wang, J., & Liu, Y. (2020) · Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2020/476 · Cited by 250
The Cramer Distance as a Solution to Biased Wasserstein Gradients
Bellemare, M. G., Danihelka, I., Dabney, W., Mohamed, S., Lakshminarayanan, B., Hoyer, S., & Munos, R. (2017) · arXiv · doi:10.48550/arxiv.1705.10743 · Cited by 223
Biometrics Systems Under Spoofing Attack: An evaluation methodology and lessons learned
Hadid, A., Evans, N., Marcel, S., & Fierrez, J. (2015) · IEEE Signal Processing Magazine · doi:10.1109/msp.2015.2437652 · Cited by 218
Bińkowski, M., Sutherland, D. J., Arbel, M., & Gretton, A. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1801.01401 · Cited by 160
Detecting Photoshopped Faces by Scripting Photoshop
Wang, S.-Y., Wang, O., Zhang, R., Owens, A., & Efros, A. (2019) · 2019 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.01017 · Cited by 135
Biometric Presentation Attack Detection: Beyond the Visible Spectrum
Tolosana, R., Gomez-Barrero, M., Busch, C., & Ortega-Garcia, J. (2019) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2019.2934867 · Cited by 109
Self-citationMultiple classifiers in biometrics. Part 2: Trends and challenges
Fierrez, J., Morales, A., Vera-Rodriguez, R., & Camacho, D. (2018) · Information Fusion · doi:10.1016/j.inffus.2017.12.005 · Cited by 91
Detection of Fake Images Via The Ensemble of Deep Representations from Multi Color Spaces
He, P., Li, H., & Wang, H. (2019) · 2019 IEEE International Conference on Image Processing (ICIP) · doi:10.1109/icip.2019.8803740 · Cited by 67
Introduction to Face Presentation Attack Detection
Hernandez‐Ortega, J., Fiérrez, J., Morales, A., & Galbally, J. (2019) · Advances in computer vision and pattern recognition · doi:10.1007/978-3-319-92627-8_9 · Cited by 61
BioTouchPass2: Touchscreen Password Biometrics Using Time-Aligned Recurrent Neural Networks
Tolosana, R., Vera-Rodriguez, R., Fierrez, J., & Ortega-Garcia, J. (2020) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2020.2973832 · Cited by 58
Self-citationDetecting GAN generated Fake Images using Co-occurrence MatricesPreprint
Nataraj, L., Mohammed, T. M., Chandrasekaran, S., et al. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1903.06836 · Cited by 54
Detecting GAN-generated Imagery using Color Cues
McCloskey, S., & Albright, M. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1812.08247 · Cited by 53
Biometric presentation attack detection: beyond the visible spectrum
Tolosana, R., Gomez Barrero, M., Busch, C., & Ortega Garcia, J. (2019) · LA Referencia (Red Federada de Repositorios Institucionales de Publicaciones Científicas) · Cited by 44
Self-citationDetecting and Simulating Artifacts in GAN Fake ImagesPreprint
Zhang, X., Karaman, S., & Chang, S.-F. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1907.06515 · Cited by 39
FakeSpotter: A Simple Baseline for Spotting AI-Synthesized Fake Faces
Wang, R., Ma, L., Juefei-Xu, F., Xie, X., Wang, J., & Liu, Y. (2019) · Cited by 39
Attributing Fake Images to GANs: Learning and Analyzing GAN Fingerprints
Yu, N., Davis, L. S., & Fritz, M. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1811.08180 · Cited by 38
Attributing Fake Images to GANs: Analyzing Fingerprints in Generated Images.Preprint
Yu, N., Davis, L. S., & Fritz, M. (2018) · arXiv (Cornell University) · Cited by 35
FakeSpotter: A Simple yet Robust Baseline for Spotting AI-Synthesized Fake FacesPreprint
Wang, R., Juefei-Xu, F., Ma, L., et al. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1909.06122 · Cited by 32
Detecting Photoshopped Faces by Scripting PhotoshopPreprint
Wang, S.-Y., Wang, O., Owens, A., et al. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1906.05856 · Cited by 27
Keystroke Biometrics in Response to Fake News Propagation in a Global Pandemic
Morales, A., Acien, A., Fiérrez, J., Monaco, J. V., Tolosana, R., Vera-Rodríguez, R., & Ortega-García, J. (2020) · IEEE Annual International Computer Software and Applications Conference (COMPSAC) · doi:10.1109/compsac48688.2020.00-26 · Cited by 27
Self-citationSource Generator Attribution via Inversion
Albright, M., & McCloskey, S. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1905.02259 · Cited by 24
Segmentation-Less and Non-Holistic Deep-Learning Frameworks for Iris Recognition
Proença, H. P. M. C., & Neves, J. C. (2019) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw.2019.00283 · Cited by 21
Self-citation
Research works printed but not linked: 1
- [18] I. Goodfellow, J. Pouget-Abadie, M. Mirza, B. Xu, D. Warde-Farley, S. Ozair, A. Courville, and Y. Bengio, 'Generative Adversarial Nets,' in Proc. Advances in Neural Information Processing Systems , 2014. -
Cited by
Deepfakes 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
Self-citationMedia Forensics and DeepFakes: An Overview
Verdoliva, L. (2020) · IEEE Journal of Selected Topics in Signal Processing · doi:10.1109/jstsp.2020.3002101 · Cited by 979
A comprehensive survey on design and application of autoencoder in deep learning
Li, P., Pei, Y., & Li, J. (2023) · Applied Soft Computing · doi:10.1016/j.asoc.2023.110176 · Cited by 602
Masood, 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
Learning Self-Consistency for Deepfake Detection
Zhao, T., Xu, X., Xu, M., Ding, H., Xiong, Y., & Xia, W. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.01475 · Cited by 383
“To detect the whole image synthesis, recent research [58, 36, 13, 52] observes that GANgenerated images contain specific cues that can be easily detected, and the trained models have exhibited good generalization ability across different synthesis methods.”
Background
Metadata
- Authors
- Neves, J. C., Tolosana, R., Vera-Rodriguez, R., Lopes, V., Proenca, H., & Fierrez, J.
- Affiliations
- University of Beira Interior (PT)
- Venue
- IEEE Journal of Selected Topics in Signal Processing
- Published
- 2020-08
- Volume
- 14
- Issue
- 5
- Pages
- 1038-1048
- ISSN
- 1932-4553 (ISSN-L)
- 1941-0484
- OpenAlex
- W3014750960
- Cited by
- 12
- References
- 52
- Citations by year
- 2024: 1 · 2023: 3 · 2022: 5 · 2020: 3
- FWCI
- 1.07
- Type
- journal article
- Language
- en
- Open access
- green
- arxiv.org
- Licence
- Locations
- IEEE Journal of Selected Topics in Signal Processing (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- Biblos-e Archivo (Universidad Autónoma de Madrid) (submittedVersion)
- arXiv (Cornell University)
- Funders
- Consejera de Educacin Juventud y Deporte de la Comunidad de Madrid y Fondo Social Europeo
- TRESPASS-ETN (H2020-MSCA-ITN-2019-860813)
- Bio-Guard (Ayudas Fundacion BBVA a Equipos de Investigacion C)
- Accenture
- BIBECA (RTI2018-101248-B-I00 MINECO/FEDER)
- NVIDIA Corporation
- NOVA LINCS (UIDB/04516/2020)
- PRIMA (H2020-MSCA-ITN-2019-860315)
- FCTMCTES (UIDB/EEA/50008/2020)
- 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 › Computer Vision and Pattern Recognition › Generative Adversarial Networks and Image Synthesis
- Keywords
- face manipulation detection, synthetic face images, spoofing attacks, steganalysis
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.