CoChat
Sign Up
Cited by 24Digital Media Forensic DetectionAdvanced Steganography and Watermarking TechniquesAdversarial Robustness in Machine Learning

The DOI matches its Crossref record; 2 of the 2 references it cites were found in a registry or an index.

Smart Watermark to Defend against Deepfake Image Manipulation

Lv, Luochen·2021·2021 IEEE 6th International Conference on Computer and Communication Systems (ICCCS)
DOI 10.1109/icccs52626.2021.9449287
Open this paper in CoChat — free account

Abstract

Deepfake image manipulation has become a serious security threat to the social network. Currently, there are limited studies on protective methods that are against Deepfake image manipulation. To tackle this problem, we here propose an adversary attack based smart watermark model, which adds unperceptive watermarks to images so that the images become adversary examples to Deepfake models. When the Deepfake manipulates these watermarked images, the manipulated images become blur. The manipulation thus can be easily recognized by human and machines. Our experiments have shown that our model outperforms the SOTA and can be used to effectively prevent Deepfake manipulation.

Overview

Integrity signals

Registry

Crossref · 10.1109/icccs52626.2021.9449287

Cites

2 of 2 references verified0 citation errors · 0 not checkable

Statistics

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

Verification

Claims the paper makes

This paper’s full text isn’t openly available, so its claims and self-check weren’t run. The registry and citation checks still apply.

Citations

Cites

Flagged first, then by citations

Show all 2 references

Research works printed but not linked: 28

  1. 10.1109/TMM.2019.2936305 · DOI
  2. wang, 2019, FakeSpotter A simple yet robust baseline for spotting AI-synthesized fake faces[J]
  3. 10.1109/CVPR42600.2020.00872 · DOI · Paper page
  4. rössler, 2018, FaceForensics A Large-scale Video Dataset for Forgery Detection in Human Faces
  5. 10.1109/CVPR42600.2020.01356 · DOI
  6. 10.1007/s13735-018-0147-1 · DOI · Paper page
  7. wang, 2020, DeepTag Robust Image Tagging for Deepfake Provenance[J]
  8. 10.1007/978-3-030-01267-0_40 · DOI
  9. 10.1109/CVPR42600.2020.00219 · DOI
  10. 10.1109/CVPR42600.2020.01356 · DOI
  11. huang, 2020, FakeRetouch Evading Deepfakes Detection via the Guidance of Deliberate Noise[J]
  12. liu, 2018, Large-scale celebfaces attributes (celeba) dataset[J], Retrieved, 15 (2018)
  13. 10.1109/CVPR42600.2020.01398 · DOI
  14. 10.1109/CISP-BMEI48845.2019.8965869 · DOI
  15. 10.1109/TNNLS.2018.2886017 · DOI · Paper page
  16. yadav, 2019, Deepfake: A survey on facial forgery technique using generative adversarial network[C]//2019, International Conference on Intelligent Computing and Control Systems (ICCS) IEEE, 852
  17. 10.1109/ACCESS.2019.2905015 · DOI
  18. 10.1109/CVPR.2018.00916 · DOI · Paper page
  19. ruiz, 2020, Disrupting Deepfakes Adversarial attacks against conditional image translation networks and facial manipulation systems[C]//European Conference on Computer Vision, 236
  20. agarwal, 2019, Protecting World Leaders Against Deep Fakes[C]//CVPR Workshops, 38
  21. 10.1016/j.inffus.2020.06.014 · DOI · Paper page
  22. 10.24963/ijcai.2018/543 · DOI
  23. xu, 2020, Generate Adversarial Examples by Nesterov-momentum Iterative Fast Gradient Sign Method[C]//2020, IEEE 11th International Conference on Software Engineering and Service Science (ICSESS), 244
  24. muncsan, 2020, Transferability of Fast Gradient Sign Method[C]//, Proceedings of SAI Intelligent Systems Conference, 23
  25. 10.1109/WACVW50321.2020.9096939 · DOI
  26. deng, 2020, Universal adversarial attack via enhanced projected gradient descent[C]//2020, IEEE International Conference on Image Processing (ICIP), 1241, 10.1109/ICIP40778.2020.9191288 · DOI
  27. xu, 2020, Real-Time Face Recognition Based on Dlib[M]//Innovative Computing, 1451
  28. 10.1109/WACVW50321.2020.9096939 · DOI

Cited by

Sorted by citations

See all 24

Metadata

Authors
Lv, L.
Affiliations
Shanghai Jiao Tong University (CN)
Corresponding author
Lv, Luochen
Venue
2021 IEEE 6th International Conference on Computer and Communication Systems (ICCCS)
Publisher
IEEE
Published
2021-04-23
Pages
380-384
DOI
10.1109/icccs52626.2021.9449287
OpenAlex
W3176547173
Cited by
24
References
2
Citations by year
2026: 4 · 2025: 4 · 2024: 6 · 2023: 7 · 2022: 3
FWCI
1.31
Type
conference paper
Language
en
Open access
closed
Licence
Locations
International Conference on Computer and Communication Systems (ICCCS) (publishedVersion)
Topics
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Digital Media Forensic Detection
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Steganography and Watermarking Techniques
  • Physical Sciences › Computer Science › Artificial Intelligence › Adversarial Robustness in Machine Learning
Keywords
deepfake detection, image watermarking, adversarial examples, image editing, image blurring, social media security

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