Towards Generalizable Deepfake Detection with Locality-aware AutoEncoder
Open accessThe DOI matches its Crossref record; 34 of the 34 references it cites were found in a registry or an index.
Abstract
With advancements of deep learning techniques, it is now possible to generate super-realistic images and videos, i.e., deepfakes. These deepfakes could reach mass audience and result in adverse impacts on our society. Although lots of efforts have been devoted to detect deepfakes, their performance drops significantly on previously unseen but related manipulations and the detection generalization capability remains a problem. Motivated by the fine-grained nature and spatial locality characteristics of deepfakes, we propose Locality-Aware AutoEncoder (LAE) to bridge the generalization gap. In the training process, we use a pixel-wise mask to regularize local interpretation of LAE to enforce the model to learn intrinsic representation from the forgery region, instead of capturing artifacts in the training set and learning superficial correlations to perform detection. We further propose an active learning framework to select the challenging candidates for labeling, which requires human masks for less than 3% of the training data, dramatically reducing the annotation efforts to regularize interpretations. Experimental results on three deepfake detection tasks indicate that LAE could focus on the forgery regions to make decisions. The analysis further shows that LAE outperforms the state-of-the-arts by 6.52%, 12.03%, and 3.08% respectively on three deepfake detection tasks in terms of generalization accuracy on previously unseen manipulations.
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 says what the claim attributes to it.
In the citing paper
“GAN-generated digital content and not actual events captured by a camera implies that they still can be detected using advanced AI models [13].”
From DFDT: An End-to-End DeepFake Detection Framework Using Vision Transformer (2022) · cites this paper as [13]
The cited source says what the claim attributes to it.
In the citing paper
“This means that these detection systems work very well when dealing with deepfakes that come from the same data distribution as they were trained on. However, they struggle to perform well when exposed to deepfakes generated using different methods than the ones used for training.”
From Deepfake Detection: Analyzing Model Generalization Across Architectures, Datasets, and Pre-Training Paradigms (2024) · 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
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 · cited 1×
“P i x e l - w i s e m a s k The Adam optimizer [19] is utilized to optimize these models with betas of 0.9 and 0.999, epsilon set to 10 − 8 , and batch size set as 64.”
MethodInfluentialGrad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization
Selvaraju, R. R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., & Batra, D. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.74 · Cited by 24,513
Xception: 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 1×
“• XceptionNet: This is a CNN network based on separable convolutions with residual connections [6].”
BackgroundLearning Deep Features for Discriminative Localization
Zhou, B., Khosla, A., Lapedriza, A., Oliva, A., & Torralba, A. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.319 · Cited by 11,428 · cited 3×
“Secondly, in our preliminary experiments we have observed that these models fail to focus on the forgery regions to make detection, leveraging heatmaps by local interpretation methods [32, 39].”
MethodDeep 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
StarGAN: Unified Generative Adversarial Networks for Multi-domain Image-to-Image Translation
Choi, Y., Choi, M., Kim, M., Ha, J.-W., Kim, S., & Choo, J. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00916 · Cited by 4,163
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 1×
“We use videos from Faceforensics++ [31].”
Generative Image Inpainting with Contextual Attention
Yu, J., Lin, Z., Yang, J., Shen, X., Lu, X., & Huang, T. S. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00577 · Cited by 2,527
Globally and locally consistent image completion
Iizuka, S., Simo-Serra, E., & Ishikawa, H. (2017) · ACM Transactions on Graphics · doi:10.1145/3072959.3073659 · Cited by 2,203 · cited 1×
“In this task we consider fake images by two inpainting methods, G&L [17] and ContextAtten [38], consisting seen and unseen dataset respectively.”
MethodMesoNet: 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
Face2Face: Real-Time Face Capture and Reenactment of RGB Videos
Thies, J., Zollhofer, M., Stamminger, M., Theobalt, C., & Niessner, M. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.262 · Cited by 1,747
International Conference on Learning Representations (ICLR)
Abbas, M. Z. A., Kivinen, J., & Raiko, T. (2016) · Cited by 1,694
Techniques for interpretable machine learning
Du, M., Liu, N., & Hu, X. (2019) · Communications of the ACM · doi:10.1145/3359786 · Cited by 1,268 · cited 1×
“CNNLocal Interpretation Local interpretation aims to identify the contributions of each feature in the input towards a specific DNN prediction [11].”
BackgroundSelf-citationTechniques for Interpretable Machine Learning
Du, M., Liu, N., & Hu, X. (2018) · arXiv · doi:10.48550/arxiv.1808.00033 · Cited by 1,261 · cited 1×
“CNNLocal Interpretation Local interpretation aims to identify the contributions of each feature in the input towards a specific DNN prediction [11].”
BackgroundSelf-citationDeepfakes 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
Face X-Ray for More General Face Forgery Detection
Li, L., Bao, J., Zhang, T., Yang, H., Chen, D., Wen, F., & Guo, B. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.00505 · Cited by 1,211
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
Self-citationCapsule-forensics: Using Capsule Networks to Detect Forged Images and Videos
Nguyen, H. H., Yamagishi, J., & Echizen, I. (2019) · ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) · doi:10.1109/icassp.2019.8682602 · Cited by 951
Farid, H. (2009) · IEEE Signal Processing Magazine · doi:10.1109/msp.2008.931079 · Cited by 925 · cited 1×
“Traditional Manipulated Forgery Detection Techniques for traditional manipulated forgery detection have existed for a long history [15].”
BackgroundA 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 · cited 1×
“• SuppressNet : A generic manipulation detector [4].”
BackgroundExploiting 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 · cited 1×
“There are generally two categories of methods for deepfake detection: hand-crafted features based methods, and deep learning based methods [25].”
MethodDemo of Face2Face: real-time face capture and reenactment of RGB videos
Thies, J., Zollhöfer, M., Stamminger, M., Theobalt, C., & Nießner, M. (2016) · ACM SIGGRAPH 2016 Emerging Technologies · doi:10.1145/2929464.2929475 · Cited by 589
Fighting 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
Cozzolino, D., Poggi, G., & Verdoliva, L. (2017) · Proceedings of the 5th ACM Workshop on Information Hiding and Multimedia Security · doi:10.1145/3082031.3083247 · Cited by 349
Distinguishing computer graphics from natural images using convolution neural networks
Rahmouni, N., Nozick, V., Yamagishi, J., & Echizen, I. (2017) · 2017 IEEE Workshop on Information Forensics and Security (WIFS) · doi:10.1109/wifs.2017.8267647 · Cited by 318 · cited 1×
“• StatsNet: This method integrates the computation of statistical feature extraction within a CNN framework [29].”
MethodForensicTransfer: Weakly-supervised Domain Adaptation for Forgery Detection
Cozzolino, D., Thies, J., Rössler, A., Riess, C., Nießner, M., & Verdoliva, L. (2018) · arXiv · doi:10.48550/arxiv.1812.02510 · Cited by 221 · cited 7×
“The most similar work to ours is ForensicTransfter method [8].”
BackgroundMethodInfluentialOn the Generalization of GAN Image Forensics
Xuan, X., Peng, B., Wang, W., & Dong, J. (2019) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-31456-9_15 · Cited by 184
Fake Face Detection Methods: Can They Be Generalized?
Khodabakhsh, A., Ramachandra, R., Raja, K., Wasnik, P., & Busch, C. (2018) · 2018 International Conference of the Biometrics Special Interest Group (BIOSIG) · doi:10.23919/biosig.2018.8553251 · Cited by 151 · cited 2×
“Firstly, as evidenced by recent work [8, 18], although current methods could achieve 99% accuracy on hold-out test set for most tasks, the performance drops to around 50% random guess accuracy on previously unseen forgery images/videos.”
BackgroundMethodDeep 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
Deep 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) · SSRN Electronic Journal · doi:10.2139/ssrn.4030341 · Cited by 112
On Attribution of Recurrent Neural Network Predictions via Additive Decomposition
Du, M., Liu, N., Yang, F., Ji, S., & Hu, X. (2019) · The World Wide Web Conference · doi:10.1145/3308558.3313545 · Cited by 54 · cited 1×
“The final interpretation is illustrated in the format of feature importance visualization [12, 13].”
BackgroundSelf-citation2017 IEEE Workshop on Information Forensics and Security (WIFS)
(2017) · doi:10.1109/wifs41869.2017 · Cited by 45
On the generalization of GAN image forensicsPreprint
Xuan, X., Peng, B., Wang, W., et al. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1902.11153 · Cited by 10 · cited 1×
“As new types of deepfake manipulations emerge quickly, unfortunately the forensic meth-ods without sufficient generalization capability cannot be readily applied to real world data [18, 37].”
Background
Research works printed but not linked: 7
- Shruti Agarwal , Hany Farid , Yuming Gu , Mingming He , Koki Nagano , and Hao Li . 2019 . Protecting World Leaders Against Deep Fakes. In The Conference on Computer Vision and Pattern Recognition (CVPR) Workshop. Shruti Agarwal, Hany Farid, Yuming Gu, Mingming He, Koki Nagano, and Hao Li. 2019. Protecting World Leaders Against Deep Fakes. In The Conference on Computer Vision and Pattern Recognition (CVPR) Workshop.
- Alexey Dosovitskiy and Thomas Brox . 2016 . Generating images with perceptual similarity metrics based on deep networks . In Thirtieth Conference on Neural Information Processing Systems (NIPS). Alexey Dosovitskiy and Thomas Brox. 2016. Generating images with perceptual similarity metrics based on deep networks. In Thirtieth Conference on Neural Information Processing Systems (NIPS).
- Mengnan Du , Ninghao Liu , Qingquan Song , and Xia Hu . 2018 . Towards Explanation of DNN-based Prediction with Guided Feature Inversion. ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD) (2018). Mengnan Du, Ninghao Liu, Qingquan Song, and Xia Hu. 2018. Towards Explanation of DNN-based Prediction with Guided Feature Inversion. ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD) (2018).
- Durk P Kingma and Prafulla Dhariwal . 2018 . Glow: Generative flow with invertible 1x1 convolutions . In Thirty-second Conference on Neural Information Processing Systems (NeurIPS). Durk P Kingma and Prafulla Dhariwal. 2018. Glow: Generative flow with invertible 1x1 convolutions. In Thirty-second Conference on Neural Information Processing Systems (NeurIPS).
- Yuezun Li and Siwei Lyu . 2019 . Exposing deepfake videos by detecting face warping artifacts . Workshop on Media Forensics (in conjuction with CVPR) (2019). Yuezun Li and Siwei Lyu. 2019. Exposing deepfake videos by detecting face warping artifacts. Workshop on Media Forensics (in conjuction with CVPR) (2019).
- Karen Simonyan and Andrew Zisserman . 2015 . Very deep convolutional networks for large-scale image recognition . The International Conference on Learning Representations (ICLR) (2015). Karen Simonyan and Andrew Zisserman. 2015. Very deep convolutional networks for large-scale image recognition. The International Conference on Learning Representations (ICLR) (2015).
- Yue Wu , Wael AbdAlmageed , and Premkumar Natarajan . 2019 . ManTra-Net: Manipulation Tracing Network for Detection and Localization of Image Forgeries With Anomalous Features. In The Conference on Computer Vision and Pattern Recognition (CVPR). Yue Wu, Wael AbdAlmageed, and Premkumar Natarajan. 2019. ManTra-Net: Manipulation Tracing Network for Detection and Localization of Image Forgeries With Anomalous Features. In The Conference on Computer Vision and Pattern Recognition (CVPR).
Cited by
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
Deepfake Detection: A Systematic Literature Review
Rana, M. S., Nobi, M. N., Murali, B., & Sung, A. H. (2022) · IEEE Access · doi:10.1109/access.2022.3154404 · Cited by 573
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
Detecting Deepfakes with Self-Blended Images
Shiohara, K., & Yamasaki, T. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.01816 · Cited by 503
“Most previous detection methods [8,16,26,30,36,48,53, 64] perform well on the in-dataset scenario where they detect forgeries they learned in training; however, some studies [15,21,33,61] have found that the detection performance significantly drops in the cross-dataset scenario where fake Landmark matching”
BackgroundMethodEnd-to-End Reconstruction-Classification Learning for Face Forgery Detection
Cao, J., Ma, C., Yao, T., Chen, S., Ding, S., & Yang, X. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.00408 · Cited by 428
Metadata
- Authors
- Du, M., Pentyala, S., Li, Y., & Hu, X.
- Affiliations
- Texas A&M University (US)
- Venue
- Proceedings of the 29th ACM International Conference on Information & Knowledge Management
- Publisher
- ACM
- Published
- 2020-10-19
- Pages
- 325-334
- ISSN
- 2155-0751 (ISSN-L)
- OpenAlex
- W3094470648
- Cited by
- 114
- References
- 26
- Citations by year
- 2026: 10 · 2025: 17 · 2024: 23 · 2023: 20 · 2022: 22 · 2021: 20 · 2020: 2
- FWCI
- 4.94
- Type
- conference paper
- Language
- en
- Open access
- green
- arxiv.org
- Locations
- ACM International Conference on Information and Knowledge Management (CIKM) (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Funders
- NSF (IIS-1900990, CNS-1816497)
- DARPA (N66001-17-2-4031)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Digital Media Forensic Detection
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Generative Adversarial Networks and Image Synthesis
- Social Sciences › Sociology and Political Science › Misinformation and Its Impacts
- Keywords
- deepfake detection, spatial locality, active learning (machine learning), video forgery 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.