Student or educator? Sign up with your school email and get 6 months of Pro free.

The DOI matches its Crossref record; 60 of the 60 references it cites were found in a registry or an index.

ProFake: Detecting Deepfakes in the Wild against Quality Degradation with Progressive Quality-adaptive Learning

Open access
Xu, Huiyu, Wang, Yaopeng, Wang, Zhibo, Ba, Zhongjie, Liu, Wenxin, Jin, Lu, Weng, Haiqin, Wei, Tao, Ren, Kui·2024·Proceedings of the 2024 on ACM SIGSAC Conference on Computer and Communications Security

Abstract

Despite the promising advances in deepfake detection on current datasets, detecting visual deepfakes in real-world scenarios (e.g., deepfake videos and live streaming on YouTube) remains a challenge due to the inherent quality degradation such as unpredictable compression employed by social media platforms. Such degradation perturbs discernible forgery clues and diminishes the effectiveness of deepfake detection methods, raising a critical safety concern to the misuse of forgery faces in real-world scenarios. In this paper, we aim to understand the impacts of real-world degradation on the robustness of deepfake detection. Particularly, we investigate the risk of degraded deepfakes towards their detection on two real-world scenarios (i.e., deepfake videos and deepfake live streaming on social media platforms). By measuring the effects of real-world degradations on the performance and representation capabilities of detection models, we reveal that real-world deepfakes can be simulated via common degradation operations (e.g., JPEG compression) as they are perceptually similar to deepfake detectors. By analyzing the training dynamics under different sequences of training samples, we observe that the training order of deepfakes progressing from non-degraded (easy) to heavily degraded (hard) enhances the adaptability of detection models to various degradation in real-world scenarios. Drawing from these observations, we present a novel deepfake detection method ProFake to enhance the robustness of deepfake detection against real-world quality degradations. ProFake enables quality-adaptive learning via progressively degrade, detect and assign weights for the training samples driven by the feedback of model performance and image quality, which ensures that our model gradually focuses on more challenging samples to achieve quality-adaptive deepfake detection. Extensive experiments show that compared with existing methods, ProFake improves deepfake detection accuracy by an average of over 10 % in real-world scenarios and by an average of over 30 % in heavily degraded scenarios, while maintaining comparable performance in detecting high-quality deepfakes.

Overview

Integrity signals

Registry

Crossref · 10.1145/3658644.3690238

Cites

60 of 60 references verified0 citation errors · 0 not checkable

Statistics

Recomputing p-values needs the paper’s full text.

Verification

Claims the paper makes

We couldn’t retrieve this paper’s full text, so its claims and self-check weren’t run. The registry and citation checks still apply.

Citations

Cites

Show all 54 references

Research works printed but not linked: 9

  1. Meng Cao, Haozhi Huang, Hao Wang, Xuan Wang, Li Shen, Sheng Wang, Linchao Bao, Zhifeng Li, and Jiebo Luo. 2020. Task-agnostic temporally consistent facial video editing. arXiv preprint arXiv:2007.01466 (2020). · arXiv
  2. Brian Dolhansky, Joanna Bitton, Ben Pflaum, Jikuo Lu, Russ Howes, Menglin Wang, and Cristian Canton Ferrer. 2020. The deepfake detection challenge (dfdc) dataset. arXiv preprint arXiv:2006.07397 (2020). · arXiv
  3. Joel Frank, Thorsten Eisenhofer, Lea Schönherr, Asja Fischer, Dorothea Kolossa, and Thorsten Holz. 2020. Leveraging frequency analysis for deep fake image recognition. In International conference on machine learning. 3247--3258.
  4. Ian Goodfellow, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron Courville, and Yoshua Bengio. 2014. Generative adversarial nets. Advances in neural information processing systems 27 (2014).
  5. Jonathan Ho, Ajay Jain, and Pieter Abbeel. 2020. Denoising diffusion probabilistic models. Advances in neural information processing systems 33 (2020), 6840--6851.
  6. Diederik P Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014). · arXiv
  7. Ryota Natsume, Tatsuya Yatagawa, and Shigeo Morishima. 2018. Rsgan: face swapping and editing using face and hair representation in latent spaces. arXiv preprint arXiv:1804.03447 (2018). · arXiv
  8. Mingxing Tan and Quoc Le. 2019. Efficientnet: Rethinking model scaling for convolutional neural networks. In International conference on machine learning. 6105--6114.
  9. Hanqing Zhao Wenbo Zhou Dongdong Chen Tianyi Wei Weiming Zhang and Nenghai Yu. 2021. Multi-attentional Deepfake Detection. (2021). arXiv:cs.CV/2103.02406 https://arxiv.org/abs/2103.02406 · DOI · Paper page

Cited by

See all 3

Metadata

Authors
Xu, H., Wang, Y., Wang, Z., Ba, Z., Liu, W., Jin, L., Weng, H., Wei, T., & Ren, K.
Affiliations
  • Zhejiang University (CN)
  • Southeast University (CN)
  • Ant Group (China) (CN)
Venue
Proceedings of the 2024 on ACM SIGSAC Conference on Computer and Communications Security
Publisher
ACM
Published
2024-12-02
Pages
2207-2221
ISSN
1543-7221 (ISSN-L)
OpenAlex
W4405181248
Cited by
2
References
54
Citations by year
2026: 2
FWCI
0.41
Type
conference paper
Language
en
Open access
Locations
ACM SIGSAC Conference on Computer and Communications Security (CCS) (publishedVersion)
Funders
National Natural Science Foundation of China (62122066, U20A20182, 2022C01018)
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
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Image and Video Quality Assessment
Keywords
deepfake detection, quality degradation, JPEG compression

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: ProFake: Detecting Deepfakes in the Wild against Quality Degradation with Progressive Quality-adaptive Learning. https://app.cochat.ai/papers/10.1145/3658644.3690238
The paper
Xu, H., Wang, Y., Wang, Z., Ba, Z., Liu, W., Jin, L., Weng, H., Wei, T., & Ren, K. (2024). ProFake: Detecting Deepfakes in the Wild against Quality Degradation with Progressive Quality-adaptive Learning. Proceedings of the 2024 on ACM SIGSAC Conference on Computer and Communications Security. https://doi.org/10.1145/3658644.3690238

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.