CoChat

Quad-Stream Deepfake Detection: Combining Spatial and Frequency Domain Analysis for Robust Video Authentication

Anand, Vaishnav, Rodriguez, Ivan Felipe · 2026 · 2026 IEEE 5th International Conference on AI in Cybersecurity (ICAIC)
Cited by 0

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.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1109/icaic67076.2026.11395676

Cites

7 of 7 references verified0 citation errors · 0 not checkable

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.

A few free checks a day · papers already verified open instantly · results are public

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

Show all 7 references

Research works printed but not linked: 16

  1. 10.1109/ICCV.2019.00009 · DOI · Paper page
  2. 10.1109/CVPR42600.2020.00327 · DOI · Paper page
  3. 10.1109/CVPR.2017.195 · DOI · Paper page
  4. 10.1109/CVPR42600.2020.00791 · DOI · Paper page
  5. Dhar, Detecting Deepfake Videos with ResNext and LSTM
  6. Malik, 2023, Frequency-based Deepfake Video Detection using Deep Learning Methods, J. Comput. Biol. Informatics, 4, 41
  7. Cheng, 2024, MSIDSnet: Integrating Spatial and Frequency Information for Deepfake Detection, IEEE Trans. Information Forensics and Security
  8. Zhu, Hidden in the Waves: Exploring DCT Artifacts for Face Forgery Detection
  9. Li, Exposing deepfake videos by detecting face warping artifacts
  10. 10.1109/LSP.2016.2603342 · DOI · Paper page
  11. 10.1109/ICCV.2017.324 · DOI · Paper page
  12. 10.5555/2969033.2969125 · doi:10.5555/2969033.2969125
  13. 10.1109/CVPR42600.2020.00813 · DOI · Paper page
  14. Ho, Denoising Diffusion Probabilistic Models
  15. Li, In Ictu Oculi: Exposing AI-Generated Fake Face Videos by Detecting Eye Blinking
  16. 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.