The DOI matches its Crossref record; 72 of the 75 references it cites were found in a registry or an index.
Implicit Identity Leakage: The Stumbling Block to Improving Deepfake Detection Generalization
Open accessAbstract
In this paper, we analyse the generalization ability of binary classifiers for the task of deepfake detection. We find that the stumbling block to their generalization is caused by the unexpected learned identity representation on images. Termed as the Implicit Identity Leakage, this phenomenon has been qualitatively and quantitatively verified among various DNNs. Furthermore, based on such understanding, we propose a simple yet effective method named the ID-unaware Deepfake Detection Model to reduce the influence of this phenomenon. Extensive experimental results demonstrate that our method outperforms the state-of-the-art in both in-dataset and cross-dataset evaluation. The code is available at https://github.com/megvii-research/CADDM.
Overview
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
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 says what the claim attributes to it.
In the citing paper
“Despite these efforts, recent methods still face challenges, often learning dataset-specific cues that fail to detect unseen forgery samples.”
From Towards More General Video-based Deepfake Detection through Facial Component Guided Adaptation for Foundation Model (2024) · cites this paper as [9]
The cited source says what the claim attributes to it.
In the citing paper
“Using Adam as the optimizer can be considered a common setting, and a substantial number of deepfake detection methods in existing literature have adopted this configuration (paper [20, 27, 26, 3, 12]).”
From DeepfakeBench: A Comprehensive Benchmark of Deepfake Detection (2023) · cites this paper as [12]
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
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
U-Net: Convolutional Networks for Biomedical Image Segmentation
Ronneberger, O., Fischer, P., & Brox, T. (2015) · Lecture notes in computer science · doi:10.1007/978-3-319-24574-4_28 · Cited by 99,404
Adam: A Method for Stochastic Optimization
Kingma, D. P., & Ba, J. (2014) · arXiv · doi:10.48550/arxiv.1412.6980 · Cited by 98,946
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
Image quality assessment: from error visibility to structural similarity
Wang, Z., Bovik, A. C., Sheikh, H. R., & Simoncelli, E. P. (2004) · IEEE Transactions on Image Processing · doi:10.1109/tip.2003.819861 · Cited by 57,892
You Only Look Once: Unified, Real-Time Object Detection
Redmon, J., Divvala, S., Girshick, R., & Farhadi, A. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.91 · Cited by 53,803
(2008) · Journal of Machine Learning Research · Cited by 33,051
(2016) · Cited by 31,590
Girshick, R. (2015) · 2015 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.169 · Cited by 28,105
Labaca-Castro, R. (2023) · Springer eBooks · doi:10.1007/978-3-658-40442-0_9 · Cited by 21,119
Research works printed but not linked: 4
- shapley, 1953, The Value of an n-person Game Contributions to the Theory of Games, 2, 307
- hernandez-ortega, 2019, Deepfake
- zhang, 0, S3fd: Single shot scale-invariant face detector, Proceedings of the IEEE International Conference on Computer Vision, 192
- kowalski, 2018, Faceswap
Cited by
Sorted by citations
UCF: Uncovering Common Features for Generalizable Deepfake Detection
Yan, Z., Zhang, Y., Fan, Y., & Wu, B. (2023) · 2023 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.02048 · Cited by 241
Transcending Forgery Specificity with Latent Space Augmentation for Generalizable Deepfake Detection
Yan, Z., Luo, Y., Lyu, S., Liu, Q., & Wu, B. (2024) · 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52733.2024.00858 · Cited by 166
“…image forgery have developed novel solutions from different directions: data augmentation [4, 28, 29, 42, 60], frequency clues [17, 33, 34, 37, 52], ID information [13, 23], disentanglement learning [32, 54, 56], designed networks [7, 59], reconstruction learning [3, 50], and 3D decomposition [64].”
BackgroundBeyond 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
DeepfakeBench: A Comprehensive Benchmark of Deepfake Detection
Yan, Z., Zhang, Y., Yuan, X., Lyu, S., & Wu, B. (2023) · arXiv · doi:10.48550/arxiv.2307.01426 · Cited by 97
NGUYEN, D., MEJRI, N., SINGH, I. P., KULESHOVA, P., ASTRID, M., KACEM, A., GHORBEL, E., & AOUADA, D. (2024) · 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52733.2024.01647 · Cited by 93
Metadata
- Authors
- Dong, S., Wang, J., Ji, R., Liang, J., Fan, H., & Ge, Z.
- Affiliations
- Megvii (China) (CN)
- Venue
- 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
- Publisher
- IEEE
- Published
- 2023-06
- Pages
- 3994-4004
- ISSN
- 1063-6919 (ISSN-L)
- OpenAlex
- W4386071484
- Cited by
- 220
- References
- 75
- Citations by year
- 2026: 57 · 2025: 95 · 2024: 62 · 2023: 6
- FWCI
- 23.53
- Type
- conference paper
- Language
- en
- Open access
- green
- arxiv.org
- Locations
- IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Digital Media Forensic Detection
- Physical Sciences › Computer Science › Signal Processing › Biometric Identification and Security
- Social Sciences › Sociology and Political Science › Misinformation and Its Impacts
- Keywords
- deepfake detection, generalization, identity representation, cross-dataset evaluation, binary classification
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
