Quad-Stream Deepfake Detection: Combining Spatial and Frequency Domain Analysis for Robust Video Authentication
The DOI matches its Crossref record; 7 of the 7 references it cites were found in a registry or an index.
Abstract
Deepfake videos poses a great challenge in cyber-security, it may deceive people to take actions that increase the vulnerability to fraud, misinformation, identity theft, and social engineering attacks. Current methods, for the most part, take as input RGB images and process them as a blackbox algorithm that learns to distinguish between real and fake. In this paper, we propose a quad-stream deepfake detection network that combines spatial and frequency domain analysis of both the face region and the entire video frame. Our approach first performs face detection and alignment to extract high-quality face crops from video frames, while also retaining the context of the whole frame. Each face crop and full-frame image is then transformed into both RGB spatial domain and frequency domain representations (via Fourier transform), yielding four parallel input streams. We design a neural network architecture with four specialized CNN-based sub-networks: two spatial streams (face and frame) using pretrained backbones, and two frequency streams (face and frame) using modified ResNet backbones for frequency spectrum input. Features from all streams are combined for final classification. The proposed method shows promising results as it is able to spot subtle forgery artifacts in both facial details and broader scene context, as well as anomalies revealed in frequency spectra that are imperceptible in raw pixels. We evaluate our model on popular deepfake video benchmarks including FaceForensics++ and Celeb-DF v2, achieving state-of-the-art detection accuracy. Notably, our quad-stream approach improves robustness under challenging conditions such as video compression and cross-dataset evaluation. An ablation study confirms that each stream (face vs. frame, spatial vs. frequency) contributes to overall performance. Our results demonstrate that integrating spatial and frequency information at multiple scales yields a significantly more generalizable deepfake detector.
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
High-Resolution Image Synthesis with Latent Diffusion Models
Rombach, R., Blattmann, A., Lorenz, D., Esser, P., & Ommer, B. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.01042 · Cited by 20,302
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
On the Detection of Digital Face Manipulation
Dang, H., Liu, F., Stehouwer, J., Liu, X., & Jain, A. K. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.00582 · Cited by 764
Two-Stream Neural Networks for Tampered Face Detection
Zhou, P., Han, X., Morariu, V. I., & Davis, L. S. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw.2017.229 · Cited by 700
Local Relation Learning for Face Forgery Detection
Chen, S., Yao, T., Chen, Y., Ding, S., Li, J., & Ji, R. (2021) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v35i2.16193 · Cited by 334
Emotions Don't Lie: An Audio-Visual Deepfake Detection Method using Affective Cues
Mittal, T., Bhattacharya, U., Chandra, R., Bera, A., & Manocha, D. (2020) · Proceedings of the 28th ACM International Conference on Multimedia · doi:10.1145/3394171.3413570 · Cited by 319
On Improving Cross-dataset Generalization of Deepfake Detectors
Nadimpalli, A. V., & Rattani, A. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw56347.2022.00019 · Cited by 79 · cited 2×
“Numerous studies have shown that detectors trained on one dataset or manipulation technique often experience substantial performance degradation when evaluated on unseen datasets, novel synthesis pipelines, or heavily compressed videos [1], [24].”
Research works printed but not linked: 16
- 10.1109/ICCV.2019.00009 · DOI · Paper page
- 10.1109/CVPR42600.2020.00327 · DOI · Paper page
- 10.1109/CVPR.2017.195 · DOI · Paper page
- 10.1109/CVPR42600.2020.00791 · DOI · Paper page
- Dhar, Detecting Deepfake Videos with ResNext and LSTM
- Malik, 2023, Frequency-based Deepfake Video Detection using Deep Learning Methods, J. Comput. Biol. Informatics, 4, 41
- Cheng, 2024, MSIDSnet: Integrating Spatial and Frequency Information for Deepfake Detection, IEEE Trans. Information Forensics and Security
- Zhu, Hidden in the Waves: Exploring DCT Artifacts for Face Forgery Detection
- Li, Exposing deepfake videos by detecting face warping artifacts
- 10.1109/LSP.2016.2603342 · DOI · Paper page
- 10.1109/ICCV.2017.324 · DOI · Paper page
- 10.5555/2969033.2969125 · doi:10.5555/2969033.2969125
- 10.1109/CVPR42600.2020.00813 · DOI · Paper page
- Ho, Denoising Diffusion Probabilistic Models
- Li, In Ictu Oculi: Exposing AI-Generated Fake Face Videos by Detecting Eye Blinking
- Li, Exposing DeepFake Videos by Detecting Face Warping Artifacts
Metadata
- Authors
- Anand, V., & Rodriguez, I. F.
- Venue
- 2026 IEEE 5th International Conference on AI in Cybersecurity (ICAIC)
- Publisher
- IEEE
- Published
- 2026-02-18
- Pages
- 1-9
- Cited by
- 0
- References
- 7
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: Quad-Stream Deepfake Detection: Combining Spatial and Frequency Domain Analysis for Robust Video Authentication. https://app.cochat.ai/papers/10.1109/icaic67076.2026.11395676
- The paper
- Anand, V., & Rodriguez, I. F. (2026). Quad-Stream Deepfake Detection: Combining Spatial and Frequency Domain Analysis for Robust Video Authentication. 2026 IEEE 5th International Conference on AI in Cybersecurity (ICAIC). https://doi.org/10.1109/icaic67076.2026.11395676
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.