Extracting Deep Local Features to Detect Manipulated Images of Human Faces
Open accessThe DOI matches its Crossref record; 13 of the 13 references it cites were found in a registry or an index.
Abstract
Recent developments in computer vision and machine learning have made it possible to create realistic manipulated videos of human faces, raising the issue of ensuring adequate protection against the malevolent effects unlocked by such capabilities. In this paper we propose local image features which are shared across manipulated regions as a key element for the automatic detection of manipulated face images. We also design a lightweight architecture with the correct structural biases for extracting such features and derive a multitask training scheme that consistently outperforms image class supervision alone. The trained networks achieve state-of-the-art results in the FaceForensics++ dataset using significantly reduced number of parameters and are shown to work well in detecting fully generated face images.
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
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 5×
“In the ablation study presented in section 4.2 we use the FF++ dataset [8] which extends FaceForensics [20] to include samples generated from Deepfakes [2] and FaceSwap [1] containing 1000 videos per manipulation method.”
BackgroundMethodResultInfluentialMesoNet: 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
Learning to Discover Cross-Domain Relations with Generative Adversarial Networks
Kim, T., Cha, M., Kim, H., Lee, J. K., & Kim, J. (2017) · arXiv · doi:10.48550/arxiv.1703.05192 · Cited by 1,716
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
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
A Deep Learning Approach to Universal Image Manipulation Detection Using a New Convolutional Layer
Bayar, B., & Stamm, M. C. (2016) · Proceedings of the 4th ACM Workshop on Information Hiding and Multimedia Security · doi:10.1145/2909827.2930786 · Cited by 838
Exposing DeepFake Videos By Detecting Face Warping Artifacts
Li, Y., & Lyu, S. (2018) · arXiv · doi:10.48550/arxiv.1811.00656 · Cited by 785 · cited 1×
“The intuition that the final image rescaling and alignment steps common in various deepfakes pipelines should introduce face warping artifacts is further explored in [13] who propose a self-supervised technique bypassing the need for expensive positive examples.”
BackgroundTwo-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
Xception: Deep Learning with Depthwise Separable Convolutions
Chollet, F. (2016) · arXiv · doi:10.48550/arxiv.1610.02357 · Cited by 538
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 · cited 1×
“shown in red cross align face regions, introduce Gaussian blur smoothing to the aligned face region and affine warp back to the size and orientation of the initial image. Testing on the datasets from [22], [39] their method appears to detect deepfakes with high accuracy. In [24] the authors take advantage of a bias of…”
Background
Research works printed but not linked: 15
- agarwal, 2019, Protecting World Leaders Against Deep Fakes, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 8
- lin, 2013, Network in Network
- nair, 2010, Rectified linear units improve restricted boltzmann machines, Proceedings of the 27th International Conference on International Conference on Machine Learning, 807
- ioffe, 2015, Batch normalization: Accelerating deep network training by reducing internal covariate shift, CoRR, abs 1502 3167
- goodfellow, 2014, Generative adversarial nets, Advances in neural information processing systems, 27, 2672
- 10.1145/3292039 · DOI · Paper page
- karras, 2018, A style-based generator architecture for generative adversarial networks, CoRR, abs 1812 4948
- karras, 2017, Progressive growing of gans for improved quality, stability, and variation, CoRR, abs 1710 10196
- 0, Deepfakes github
- kowalski, 0, Faceswap
- rahmouni, 2017, Distinguishing computer graphics from natural images using convolution neural networks, IEEE Workshop on Information Forensics and Security (WIFS) 2010, 1
- rössler, 2018, Faceforensics: A large-scale video dataset for forgery detection in human faces, CoRR, abs 1803 9179
- alexey, 2019, Deepfakes detection dataset by google & jigsaw
- deng, 2019, Retinaface: Single-stage dense face localisation in the wild, CoRR, abs 1905 641
- li, 2019, Celeb-DF A new dataset for deepfake forensics
Cited by
Lips Don't Lie: A Generalisable and Robust Approach to Face Forgery Detection
Haliassos, A., Vougioukas, K., Petridis, S., & Pantic, M. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr46437.2021.00500 · Cited by 537
“Some methods [5, 49] predict the manipulated region along with the label in a multi-task fashion.”
MethodA Survey on Deepfake Video Detection
Yu, P., Xia, Z., Fei, J., & Lu, Y. (2021) · IET Biometrics · doi:10.1049/bme2.12031 · Cited by 253
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
“, 2018), CNN with local features (Tarasiou and Zafeiriou, 2020), CNN with optical flow (Amerini et al.”
BackgroundDas, S., Seferbekov, S., Datta, A., Islam, M. S., & Amin, M. R. (2021) · 2021 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW) · doi:10.1109/iccvw54120.2021.00421 · Cited by 107
“As a result of these efforts, a large number of deepfake detection approaches [27, 15, 44, 46, 47, 14], as well as a number of datasets [10, 8, 50, 31, 19, 39] have been proposed in recent times.”
Deepfake Detection for Facial Images with Facemasks
Ko, D., Lee, S., Park, J., Shin, S., Hong, D., & Woo, S. S. (2022) · arXiv · doi:10.48550/arxiv.2202.11359 · Cited by 10
Metadata
- Authors
- Tarasiou, M., & Zafeiriou, S.
- Venue
- 2020 IEEE International Conference on Image Processing (ICIP)
- Publisher
- IEEE
- Published
- 2020-10
- Pages
- 1821-1825
- ISSN
- 1522-4880 (ISSN-L)
- OpenAlex
- W3006015659
- Cited by
- 21
- References
- 13
- FWCI
- 1.05
- Type
- conference paper
- Language
- en
- Open access
- green
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
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Extracting Deep Local Features to Detect Manipulated Images of Human Faces. https://app.cochat.ai/papers/10.1109/icip40778.2020.9190714
- The paper
- Tarasiou, M., & Zafeiriou, S. (2020). Extracting Deep Local Features to Detect Manipulated Images of Human Faces. 2020 IEEE International Conference on Image Processing (ICIP). https://doi.org/10.1109/icip40778.2020.9190714
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.