CoChat

DefakeHop: A Light-Weight High-Performance Deepfake Detector

Open access
Chen, Hong-Shuo, Rouhsedaghat, Mozhdeh, Ghani, Hamza, Hu, Shuowen, You, Suya, Jay Kuo, C.-C. · 2021 · 2021 IEEE International Conference on Multimedia and Expo (ICME)
Cited by 100

The DOI matches its Crossref record; 10 of the 10 references it cites were found in a registry or an index.

Abstract

A light-weight high-performance Deepfake detection method, called DefakeHop, is proposed in this work. State-of-the-art Deepfake detection methods are built upon deep neural networks. DefakeHop uses the successive subspace learning (SSL) principle to extracts features automatically from various parts of face images. The features are extracted by channel-wise (c/w) Saab transform and further processed by our feature distillation module using spatial dimension re-duction and soft classification for each channel to get a more concise description of the face. Extensive experiments are conducted to demonstrate the effectiveness of the proposed DefakeHop method. With a small model size of 42,845 parameters, DefakeHop achieves state-of-the-art performance with the area under the ROC curve (AUC) of 100%, 94.95%, and 90.56% on UADFV, Celeb-DF v1, and Celeb-DF v2 datasets, respectively. Our codes are available on GitHub1.

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/icme51207.2021.9428361

Cites

10 of 10 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 10 references

Research works printed but not linked: 6

  1. agarwal, 2019, Protecting world leaders against deep fakes, CVPR Workshops, 38
  2. 10.1109/ICIP40778.2020.9191012 · DOI
  3. jay kuo, 2016, Understanding convolutional neural net-works with a mathematical model, Journal of Visual Communication and Image Representation, 41, 406, 10.1016/j.jvcir.2016.11.003 · DOI · Paper page
  4. jay kuo, 2019, Interpretable convolutional neural net-works via feedforward design, Journal of Visual Communication and Image Representation, 60, 346, 10.1016/j.jvcir.2019.03.010 · DOI · Paper page
  5. 10.1109/FG.2018.00019 · DOI · Paper page
  6. güera, 2018, Deepfake video detection using recurrent neural networks, 2018 15th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS), 1

Cited by

See all 100

Metadata

Authors
Chen, H.-S., Rouhsedaghat, M., Ghani, H., Hu, S., You, S., & Jay Kuo, C.-C.
Venue
2021 IEEE International Conference on Multimedia and Expo (ICME)
Publisher
IEEE
Published
2021-07-05
Pages
1-6
OpenAlex
W3169588269
Cited by
100
References
10
FWCI
6.84
Type
conference paper
Language
en
Open access
green
Funders
Army Research Laboratory

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: DefakeHop: A Light-Weight High-Performance Deepfake Detector. https://app.cochat.ai/papers/10.1109/icme51207.2021.9428361
The paper
Chen, H.-S., Rouhsedaghat, M., Ghani, H., Hu, S., You, S., & Jay Kuo, C.-C. (2021). DefakeHop: A Light-Weight High-Performance Deepfake Detector. 2021 IEEE International Conference on Multimedia and Expo (ICME). https://doi.org/10.1109/icme51207.2021.9428361

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.