Beyond the Spectrum: Detecting Deepfakes via Re-Synthesis
Open accessAbstract
The rapid advances in deep generative models over the past years have led to highly realistic media, known as deepfakes, that are commonly indistinguishable from real to human eyes. These advances make assessing the authenticity of visual data increasingly difficult and pose a misinformation threat to the trustworthiness of visual content in general. Although recent work has shown strong detection accuracy of such deepfakes, the success largely relies on identifying frequency artifacts in the generated images, which will not yield a sustainable detection approach as generative models continue evolving and closing the gap to real images. In order to overcome this issue, we propose a novel fake detection that is designed to re-synthesize testing images and extract visual cues for detection. The re-synthesis procedure is flexible, allowing us to incorporate a series of visual tasks - we adopt super-resolution, denoising and colorization as the re-synthesis. We demonstrate the improved effectiveness, cross-GAN generalization, and robustness against perturbations of our approach in a variety of detection scenarios involving multiple generators over CelebA-HQ, FFHQ, and LSUN datasets. Source code is available at https://github.com/SSAW14/BeyondtheSpectrum.
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
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.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
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 · see citing works
Unpaired image-to-image translation using cycle-consistent adversarial networks
Zhu, J.-Y., Park, T., Isola, P., & Efros, A. A. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.244 · Cited by 23,602 · see citing works
Labaca-Castro, R. (2023) · Springer eBooks · doi:10.1007/978-3-658-40442-0_9 · Cited by 21,100 · see citing works
A 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 · see citing works
Perceptual Losses for Real-Time Style Transfer and Super-Resolution
Johnson, J., Alahi, A., & Fei-Fei, L. (2016) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-46475-6_43 · Cited by 11,283 · see citing works
Improved training of Wasserstein GANs
Gulrajani, I., Ahmed, F., Arjovsky, M., Dumoulin, V., & Courville, A. (2017) · arXiv · doi:10.48550/arxiv.1704.00028 · Cited by 6,800 · see citing works
Analyzing and Improving the Image Quality of StyleGAN
Karras, T., Laine, S., Aittala, M., Hellsten, J., Lehtinen, J., & Aila, T. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.00813 · Cited by 6,332 · see citing works
High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs
Wang, T.-C., Liu, M.-Y., Zhu, J.-Y., Tao, A., Kautz, J., & Catanzaro, B. (2018) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2018.00917 · Cited by 4,514 · see citing works
Residual Dense Network for Image Super-Resolution
Zhang, Y., Tian, Y., Kong, Y., Zhong, B., & Fu, Y. (2018) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2018.00262 · Cited by 4,371 · see citing works
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 · see citing works
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 · see citing works
Generative Adversarial Text to Image Synthesis
Reed, S., Akata, Z., Yan, X., Logeswaran, L., Schiele, B., & Lee, H. (2016) · arXiv · doi:10.48550/arxiv.1605.05396 · Cited by 2,494 · see citing works
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 · see citing works
StarGAN v2: Diverse Image Synthesis for Multiple Domains
Choi, Y., Uh, Y., Yoo, J., & Ha, J.-W. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.00821 · Cited by 1,663 · see citing works
LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the LoopPreprint
Yu, F., Seff, A., Zhang, Y., Song, S., Funkhouser, T., & Xiao, J. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1506.03365 · Cited by 1,339 · see citing works
Thinking in Frequency: Face Forgery Detection by Mining Frequency-Aware Clues
Qian, Y., Yin, G., Sheng, L., Chen, Z., & Shao, J. (2020) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-58610-2_6 · Cited by 1,058 · see citing works
Detecting and Simulating Artifacts in GAN Fake Images
Zhang, X., Karaman, S., & Chang, S.-F. (2019) · 2019 IEEE International Workshop on Information Forensics and Security (WIFS) · doi:10.1109/wifs47025.2019.9035107 · Cited by 567 · see citing works
Attributing Fake Images to GANs: Learning and Analyzing GAN Fingerprints
Yu, N., Davis, L. S., & Fritz, M. (2019) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00765 · Cited by 491 · see citing works
Self-citationTwo-Branch Recurrent Network for Isolating Deepfakes in Videos
Masi, I., Killekar, A., Mascarenhas, R. M., Gurudatt, S. P., & AbdAlmageed, W. (2020) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-58571-6_39 · Cited by 471 · see citing works
Global Texture Enhancement for Fake Face Detection in the Wild
Liu, Z., Qi, X., & Torr, P. H. S. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.00808 · Cited by 401 · see citing works
Detection of GAN-Generated Fake Images over Social Networks
Marra, F., Gragnaniello, D., Cozzolino, D., & Verdoliva, L. (2018) · 2018 IEEE Conference on Multimedia Information Processing and Retrieval (MIPR) · doi:10.1109/mipr.2018.00084 · Cited by 399 · see citing works
Leveraging Frequency Analysis for Deep Fake Image Recognition
Frank, J., Eisenhofer, T., Schönherr, L., Fischer, A., Kolossa, D., & Holz, T. (2020) · arXiv · doi:10.48550/arxiv.2003.08685 · Cited by 390 · see citing works
Do GANs leave artificial fingerprints?
Marra, F., Gragnaniello, D., Verdoliva, L., & Poggi, G. (2019) · 2019 IEEE Conference on Multimedia Information Processing and Retrieval (MIPR) · doi:10.1109/mipr.2019.00103 · Cited by 361 · see citing works
What Makes Fake Images Detectable? Understanding Properties that Generalize
Chai, L., Bau, D., Lim, S.-N., & Isola, P. (2020) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-58574-7_7 · Cited by 357 · see citing works
Detecting GAN generated Fake Images using Co-occurrence Matrices
Nataraj, L., Mohammed, T. M., Manjunath, B. S., Chandrasekaran, S., Flenner, A., Bappy, J. H., & Roy-Chowdhury, A. K. (2019) · Electronic Imaging · doi:10.2352/issn.2470-1173.2019.5.mwsf-532 · Cited by 331 · see citing works
Artificial Fingerprinting for Generative Models: Rooting Deepfake Attribution in Training Data
Yu, N., Skripniuk, V., Abdelnabi, S., & Fritz, M. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.01418 · Cited by 195 · see citing works
Self-citationUnmasking DeepFakes with simple Features
Durall, R., Keuper, M., Pfreundt, F.-J., & Keuper, J. (2019) · arXiv · doi:10.48550/arxiv.1911.00686 · Cited by 184 · see citing works
Self-citationA Full-Image Full-Resolution End-to-End-Trainable CNN Framework for Image Forgery Detection
Marra, F., Gragnaniello, D., Verdoliva, L., & Poggi, G. (2020) · IEEE Access · doi:10.1109/access.2020.3009877 · Cited by 140 · see citing works
Dual Contrastive Loss and Attention for GANs
Yu, N., Liu, G., Dündar, A., Tao, A., Catanzaro, B., Davis, L. S., & Fritz, M. (2021) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00666 · Cited by 57 · see citing works
Self-citationTexture Mixer: A Network for Controllable Synthesis and Interpolation of Texture
Yu, N., Barnes, C., Shechtman, E., Amirghodsi, S., & Lukáč, M. (2019) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2019.01244 · Cited by 51 · see citing works
Self-citationInclusive GAN: Improving Data and Minority Coverage in Generative Models
Yu, N., Li, K., Zhou, P., Malik, J., Davis, L., & Fritz, M. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-58542-6_23 · Cited by 45 · see citing works
Self-citationResponsible Disclosure of Generative Models Using Scalable FingerprintingPreprint
Yu, N., Skripniuk, V., Chen, D., Davis, L. S., & Fritz, M. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2012.08726 · Cited by 38 · see citing works
Self-citationHijack-GAN: Unintended-Use of Pretrained, Black-Box GANs
Wang, H., Yu, N., & Fritz, M. (2021) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr46437.2021.00778 · Cited by 30 · see citing works
Self-citationDurall, R., Keuper, M., & Keuper, J. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.00791 · Cited by 26 · see citing works
Self-citationOn Attribution of DeepfakesPreprint
Zhang, B., Zhou, J., Shumailov, I., & Papernot, N. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2008.09194 · Cited by 14 · see citing works
Not My Deepfake: Towards Plausible Deniability for Machine-Generated MediaPreprint
Zhang, B., Zhou, J., Shumailov, I., & Papernot, N. (2020) · arXiv (Cornell University) · Cited by 9 · see citing works
Spectral Distribution Aware Image Generation
Jung, S., & Keuper, M. (2021) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v35i2.16267 · Cited by 7 · see citing works
Self-citationHijack-GAN: Unintended-Use of Pretrained, Black-Box GANsPreprint
Wang, H., Yu, N., & Fritz, M. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2011.14107 · Cited by 7 · see citing works
Self-citationDual Contrastive Loss and Attention for GANsPreprint
Yu, N., Liu, G., Dündar, A., Tao, A., Catanzaro, B., Davis, L. S., & Fritz, M. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2103.16748 · Cited by 5 · see citing works
Self-citationArtificial Fingerprinting for Generative Models: Rooting Deepfake Attribution in Training DataPreprint
Yu, N., Skripniuk, V., Abdelnabi, S., et al. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2007.08457 · Cited by 3 · see citing works
Self-citation
Flagged first, then by citations
Research works printed but not linked: 4
- [12]12. Ian Goodfellow, Jean Pouget- Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron Courville, and Yoshua Bengio. Gen- erative adversarial nets. In NeurIPS, 2014.
- [22]22. Tero Karras, Timo Aila, Samuli Laine, and Jaakko Lehtinen. Progressive growing of gans for im- proved quality, stability, and variation. In ICLR, 2018.
- [38]38. Radford et al., 2016] Alec Radford, Luke Metz, and Soumith Chintala. Unsupervised representation learning with deep convolutional generative adversarial networks. ICLR, 2016.
- [48]48. Sheng-Yu Wang, Oliver Wang, Richard Zhang, Andrew Owens, and Alexei A Efros. Cnn- generated images are surprisingly easy to spot... for now. In CVPR, 2020.
Cited by
Sorted by citations
Tan, C., Zhao, Y., Wei, S., Gu, G., Liu, P., & Wei, Y. (2024) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v38i5.28310 · Cited by 215 · see citing works
Artificial Fingerprinting for Generative Models: Rooting Deepfake Attribution in Training Data
Yu, N., Skripniuk, V., Abdelnabi, S., & Fritz, M. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.01418 · Cited by 195 · see citing works
Self-citationFrePGAN: Robust Deepfake Detection Using Frequency-Level Perturbations
Jeong, Y., Kim, D., Ro, Y., & Choi, J. (2022) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v36i1.19990 · Cited by 137 · see citing works
C2P-CLIP: Injecting Category Common Prompt in CLIP to Enhance Generalization in Deepfake Detection
Tan, C., Tao, R., Liu, H., Gu, G., Wu, B., Zhao, Y., & Wei, Y. (2025) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v39i7.32772 · Cited by 44 · see citing works
LEDNet: a multimodal foundation model for robust deepfake detection
Tao, R., Tang, S., Qin, H., Wang, W., Wei, Y., & Zhao, Y. (2025) · Science China Information Sciences · doi:10.1007/s11432-024-4400-8 · Cited by 9 · see citing works
From Black Boxes to Glass Boxes: Explainable AI for Trustworthy Deepfake Forensics
Qian, H., Xia, L., Ge, R., Fan, Y., Wang, Q., & Jing, Z. (2025) · Cryptography · doi:10.3390/cryptography9040061 · Cited by 10 · see citing works
“He et al. [21] argued that reliance on static frequency artifacts is unsustainable as generative quality improves.”
Evolving from Single-modal to Multi-modal Facial Deepfake Detection: Progress and Challenges
Liu, P., Tao, Q., & Zhou, J. T. (2024) · arXiv · doi:10.48550/arxiv.2406.06965 · Cited by 6 · see citing works
Nguyen-Le, H.-H., Tran, V.-T., Nguyen, D.-T., & Le-Khac, N.-A. (2026) · Artificial Intelligence Review · doi:10.1007/s10462-026-11608-4 · Cited by 1 · see citing works
- Authors
- He, Y., Yu, N., Keuper, M., & Fritz, M.
- Affiliations
- Helmholtz Center for Information Security (DE)
- Max Planck Institute for Informatics (DE)
- University of Mannheim (DE)
- Venue
- Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence
- Published
- 2021-08
- Pages
- 2534-2541
- OpenAlex
- W3187526215
- Cited by
- 70
- References
- 40
- Citations by year
- 2026: 8 · 2025: 19 · 2024: 19 · 2023: 17 · 2022: 5 · 2021: 2
- FWCI
- 3.52
- Type
- conference paper
- Language
- en
- Open access
- bronze
- doi.org
- Locations
- International Joint Conference on Artificial Intelligence (publishedVersion)
- 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, resynthesis, super-resolution, image denoising, image colorization, generative adversarial networks, robustness to disturbances, visual authenticity, misinformation
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
