Detect and locate: Exposing face manipulation by semantic-and noise-level telltales
Open accessThe DOI matches its Crossref record; 62 of the 62 references it cites were found in a registry or an index.
Abstract
The technological advancements of deep learning have enabled sophisticated face manipulation schemes, raising severe trust issues and security concerns in modern society. Generally speaking, detecting manipulated faces and locating the potentially altered regions are challenging tasks. Herein, we propose a conceptually simple but effective method to efficiently detect forged faces in an image while simultaneously locating the manipulated regions. The proposed scheme relies on a segmentation map that delivers meaningful high-level semantic information clues about the image. Furthermore, a noise map is estimated, playing a complementary role in capturing low-level clues and subsequently empowering decision-making. Finally, the features from these two modules are combined to distinguish fake faces. Extensive experiments show that the proposed model achieves state-of-the-art detection accuracy and remarkable localization performance.
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
“The rationale behind these methods is that deepfake generators can reproduce low-level features but struggle with more complex aspects, making it possible to differentiate between real and synthetic data.”
From A Robust Approach to Multimodal Deepfake Detection (2023) · cites this paper as [10]
In the citing paper
“For instance, there exists a set of detectors known as semantic, which base their predictions on high-level aspects of the media under analysis [9,10].”
From A Robust Approach to Multimodal Deepfake Detection (2023) · cites this paper as [10]
Citations
Cites
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474
Very Deep Convolutional Networks for Large-Scale Image Recognition
Simonyan, K., & Zisserman, A. (2014) · arXiv · doi:10.48550/arxiv.1409.1556 · Cited by 114,148 · cited 1×
“In this part, we further apply the proposed twostream multi-scale learning architecture on the VGG16 [61] and EfficientNet [56] backbones to verify that our framework can be conveniently transferred to other detectors in a plugand-play manner.”
MethodAdam: A Method for Stochastic Optimization
Kingma, D. P., & Ba, J. (2014) · arXiv · doi:10.48550/arxiv.1412.6980 · Cited by 98,946 · cited 1×
“The model is trained using Adam optimizer [42] with β1=0.”
MethodImageNet: 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×
“We conduct a two-step training strategy: 1) training the Xception backbone and the semantic map prediction module, where the weights of the backbone are initialized with the ImageNet [43] weights; and 2) initializing the weights of the Xception backbone and the semantic map prediction module with the weights obtained…”
MethodFully convolutional networks for semantic segmentation
Long, J., Shelhamer, E., & Darrell, T. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298965 · Cited by 38,834
PyTorch: An Imperative Style, High-Performance Deep Learning Library
Paszke, A., Gross, S., Massa, F., Lerer, A., Bradbury, J., Chanan, G., Killeen, T., Lin, Z., Gimelshein, N., Antiga, L., et al. (2019) · arXiv · doi:10.48550/arxiv.1912.01703 · Cited by 31,473 · cited 1×
“The proposed framework is implemented by Pytorch [41].”
MethodXception: 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 · cited 2×
“We employ the Xception network [33] as the backbone to learn multi-scale feature maps based on two insights.”
MethodEfficientNet: 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×
“In this part, we apply the designed two-stream learning scheme on both Xception and EfficientNet backbones, which are respectively denoted as Ours (Xcep.) and Ours (Effi.) in Table V.”
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 · cited 3×
“Herein, we employ the popular StyleGAN [57] and PGGAN [58] to produce 40000 entirely synthetic faces and use StarGAN [59] and AttGAN [60] to generate 40000 attribute-manipulated faces (two attribute manipulations are considered in this paper: glasses and hairs).”
MethodProgressive 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 · cited 3×
“Herein, we employ the popular StyleGAN [57] and PGGAN [58] to produce 40000 entirely synthetic faces and use StarGAN [59] and AttGAN [60] to generate 40000 attribute-manipulated faces (two attribute manipulations are considered in this paper: glasses and hairs).”
Method
Research works printed but not linked: 4
- 2018, Github Deepfake Faceswap
- 2019, Deepfakes Faceswap
- 2018, Fakeapp
- 2020, Deepfakedetection
Cited by
Beyond the Prior Forgery Knowledge: Mining Critical Clues for General Face Forgery Detection
Luo, A., Kong, C., Huang, J., Hu, Y., Kang, X., & Kot, A. C. (2024) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2023.3332218 · Cited by 115
“Powerful as deep models are, recent works take the Xception [37] and EfficientNet [28] as backbone and incorporate various types of prior knowledge to boost the detection performance [21], [38], [39], [40], [41], [42], [43], [44], [45], [46], [47], [48], [49], [50], [51], [52], [53].”
BackgroundMethodSelf-citationA Robust Approach to Multimodal Deepfake Detection
Salvi, D., Liu, H., Mandelli, S., Bestagini, P., Zhou, W., Zhang, W., & Tubaro, S. (2023) · Journal of Imaging · doi:10.3390/jimaging9060122 · Cited by 96
“In this section we introduce the reader to the deepfake detection task, providing a literature overview for the visual-only, audio-only and audio-visual deepfake detection scenarios.”
Pixel-Inconsistency Modeling for Image Manipulation Localization
Kong, C., Luo, A., Wang, S., Li, H., Rocha, A. D. R., & Kot, A. C. (2025) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2025.3541028 · Cited by 121
“The forgery images exhibit high-level harmonization, with the forgery regions having compatible illumination, reasonable size, semantic consistency, and appropriate position.”
Self-citationGuo, Z., Jia, Z., Wang, L., Wang, D., Yang, G., & Kasabov, N. K. (2023) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2023.3324739 · Cited by 101
“The alternative way is to design a new detection module, which can be embedded into the existing backbone network to promote feature learning [17], [18], [19], [20].”
BackgroundMoE-FFD: Mixture of Experts for Generalized and Parameter-Efficient Face Forgery Detection
Kong, C., Luo, A., Bao, P., Yu, Y., Li, H., Zheng, Z., Wang, S., & Kot, A. C. (2025) · IEEE Transactions on Dependable and Secure Computing · doi:10.1109/tdsc.2025.3604443 · Cited by 106
“Many of them employ Xception network [9] or EfficientNet [10] as backbones due to their outstanding performance in face forgery detection.”
Self-citation
Metadata
- Authors
- Kong, C., Chen, B., Li, H., Wang, S., Rocha, A., & Kwong, S.
- Affiliations
- City University of Hong Kong (HK)
- Universidade Estadual de Campinas (UNICAMP) (BR)
- Venue
- IEEE Transactions on Information Forensics and Security
- Published
- 2022
- Volume
- 17
- Pages
- 1741-1756
- ISSN
- 1556-6013 (ISSN-L)
- 1556-6021
- OpenAlex
- W4287080402
- Cited by
- 120
- References
- 59
- Citations by year
- 2026: 29 · 2025: 45 · 2024: 24 · 2023: 21 · 2022: 1
- FWCI
- 7.44
- Type
- journal article
- Language
- en
- Open access
- green
- arxiv.org
- Licence
- Locations
- IEEE Transactions on Information Forensics and Security (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Funders
- Shenzhen Virtual University Park, Science Technology and Innovation Committee of Shenzhen Municipality (2021Szvup128)
- National Natural Science Foundation of China (62022002)
- Hong Kong Research Grants Council General Research Fund (11203220)
- CityU New Research Initiatives/Infrastructure Support from Central (APRC 9610528)
- São Paulo Research Foundation (DéjàVu 2017/12646-3)
- 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, deepfake detection, image forgery detection, multimodal fusion
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: Detect and locate: Exposing face manipulation by semantic-and noise-level telltales. https://app.cochat.ai/papers/10.1109/tifs.2022.3169921
- The paper
- Kong, C., Chen, B., Li, H., Wang, S., Rocha, A., & Kwong, S. (2022). Detect and locate: Exposing face manipulation by semantic-and noise-level telltales. IEEE Transactions on Information Forensics and Security. https://doi.org/10.1109/tifs.2022.3169921
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.