How Do the Hearts of Deep Fakes Beat? Deep Fake Source Detection via Interpreting Residuals with Biological Signals
Open accessThe DOI matches its Crossref record; 26 of the 26 references it cites were found in a registry or an index.
Abstract
Fake portrait video generation techniques have been posing a new threat to the society with photorealistic deep fakes for political propaganda, celebrity imitation, forged evidences, and other identity related manipulations. Following these generation techniques, some detection approaches have also been proved useful due to their high classification accuracy. Nevertheless, almost no effort was spent to track down the source of deep fakes. We propose an approach not only to separate deep fakes from real videos, but also to discover the specific generative model behind a deep fake. Some pure deep learning based approaches try to classify deep fakes using CNNs where they actually learn the residuals of the generator. We believe that these residuals contain more information and we can reveal these manipulation artifacts by disentangling them with biological signals. Our key observation yields that the spatiotemporal patterns in biological signals can be conceived as a representative projection of residuals. To justify this observation, we extract PPG cells from real and fake videos and feed these to a state-of-the-art classification network for detecting the generative model per video. Our results indicate that our approach can detect fake videos with 97.29% accuracy, and the source model with 93.39% accuracy.
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
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
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 2×
“In this case, our method outperforms even the most complex network, Xception [20], with more than 10% accuracy.”
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 4×
“Although there exist several synthetic face image datasets [35, 1, 49], here we focus on video datasets due to the absence of biological signals in single images.”
BackgroundMethodInfluentialProgressive 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
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×
“In our experiments we achieve 93.39% accuracy on FaceForensics++ [53] dataset on source detection from four deep fake generators and real videos.”
MethodInfluentialMesoNet: 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
Celeb-DF: A Large-Scale Challenging Dataset for DeepFake Forensics
Li, Y., Yang, X., Sun, P., Qi, H., & Lyu, S. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.00327 · Cited by 1,846 · cited 4×
“To justify that our approach can extend to new models, we combine our FF setup with the single generator dataset CelebDF[42] and repeat the analysis.”
BackgroundMethodInfluentialFace2Face: 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
Digital Camera Identification From Sensor Pattern Noise
Luka, J., Fridrich, J., & Goljan, M. (2006) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2006.873602 · Cited by 1,328 · cited 2×
“To our knowledge, most existing deep fake source detectors are image-based, and exploit various attributes of synthetic imagery such as GAN model fingerprints [69, 25, 44, 28], camera patterns [43], or image attribution [13].”
BackgroundDeepfake Video Detection Using Recurrent Neural Networks
Guera, D., & Delp, E. J. (2018) · 2018 15th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS) · doi:10.1109/avss.2018.8639163 · Cited by 1,285
Cited by
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
DeepFake Detection Based on Discrepancies Between Faces and Their Context
Nirkin, Y., Wolf, L., Keller, Y., & Hassner, T. (2022) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2021.3093446 · Cited by 312
“Recently, detection methods have been proposed that focus on liveliness and other specific authenticity signals such as heartbeat [13], [14] and specular highlights [15].”
BackgroundCountering 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
“FakeCatcher (Ciftci et al., 2020a) has collected over 140 online videos, up to 30GB. Unlike most of the fake datasets, it includes “in the wild” videos, independent of the generative model, resolution, compression, content, and context. iFakeFaceDB (Neves et al., 2020) is a fake image dataset for…”
BackgroundMethodDeepfake generation and detection, a survey
Zhang, T. (2022) · Multimedia Tools and Applications · doi:10.1007/s11042-021-11733-y · Cited by 176
Deepfakes Detection Techniques Using Deep Learning: A Survey
Almars, A. M. (2021) · Journal of Computer and Communications · doi:10.4236/jcc.2021.95003 · Cited by 143
“[35] for example has designed a Generative Adversarial Network (GAN) based model that can detect the deepfake video source by analyzing the “heartbeat” of deep fakes.”
A review of deep learning‐based approaches for deepfake content detection
(2024) · doi:10.1111/exsy.13570 · Cited by 116
Detecting Deepfake Videos with Temporal Dropout 3DCNN
Zhang, D., Li, C., Lin, F., Zeng, D., & Ge, S. (2021) · Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2021/178 · Cited by 77
Deepfake forensics analysis: An explainable hierarchical ensemble of weakly supervised models
Silva, S. H., Bethany, M., Votto, A. M., Scarff, I. H., Beebe, N., & Najafirad, P. (2022) · Forensic Science International: Synergy · doi:10.1016/j.fsisyn.2022.100217 · Cited by 66
“[44] the authors use the pulse extracted from the video as a feature for deepfake detection.”
MethodVisual Deepfake Detection: Review of Techniques, Tools, Limitations, and Future Prospects
Ur Rehman Ahmed, N., Badshah, A., Adeel, H., Tajammul, A., Daud, A., & Alsahfi, T. (2025) · IEEE Access · doi:10.1109/access.2024.3523288 · Cited by 45
A Review of Deep Learning-based Approaches for Deepfake Content Detection
Passos, L. A., Jodas, D., Costa, K. A. P., Júnior, L. A. S., Rodrigues, D., Ser, J. D., Camacho*, D., & Papa, J. (2023) · doi:10.22541/au.169735672.27713914/v1 · Cited by 116
Using Deep Learning to Detecting Deepfakes
Mallet, J., Dave, R., Seliya, N., & Vanamala, M. (2022) · 2022 9th International Conference on Soft Computing & Machine Intelligence (ISCMI) · doi:10.1109/iscmi56532.2022.10068449 · Cited by 26
Narayan, K., Agarwal, H., Thakral, K., Mittal, S., Vatsa, M., & Singh, R. (2022) · 2022 IEEE International Joint Conference on Biometrics (IJCB) · doi:10.1109/ijcb54206.2022.10007968 · Cited by 26
“[23] have proposed a GAN based framework that utilizes the variation in heartbeat of deepfake videos to find the source method using which the deepfake was generated.”
MethodTowards mitigating uncann(eye)ness in face swaps via gaze-centric loss terms
Wilson, E., Shic, F., Jörg, S., & Jain, E. (2024) · arXiv · doi:10.48550/arxiv.2402.03188 · Cited by 4
Metadata
- Authors
- Ciftci, U. A., Demir, I., & Yin, L.
- Venue
- 2020 IEEE International Joint Conference on Biometrics (IJCB)
- Publisher
- IEEE
- Published
- 2020-09-28
- Pages
- 1-10
- OpenAlex
- W3118709007
- Cited by
- 115
- References
- 26
- FWCI
- 5.35
- 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
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.