journal article·2025Open access

Enhancing Deepfake Detection: Proactive Forensics Techniques Using Digital Watermarking

Zhimao Lai

Computers, Materials & Continua· Volume 82· Issue 1

Abstract

With the rapid advancement of visual generative models such as Generative Adversarial Networks (GANs) and stable Diffusion, the creation of highly realistic Deepfake through automated forgery has significantly progressed. Thi... | Find, read and cite all the research you need on Tech Science Press
Source: openalex_inverted_index · Quality: baseline

Research context

OpenAlex topics: Advanced Steganography and Watermarking Techniques · Digital Media Forensic Detection · Generative Adversarial Networks and Image Synthesis

SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.

References (87)

Show source-provided references
1. Deepfake the menace: Mitigating the negative impacts of AI-generated content
2. Countering malicious deepfakes: Survey, battleground, and horizon10.1007/s11263-022-01606-8 ↗
3. Deepfakes generation and detection: State-of-the-art, open challenges, countermeasures, and way forward10.1007/s10489-022-03766-z ↗
4. Towards benchmarking and evaluating deepfake detection10.1109/TDSC.2024.3369711 ↗
5. Reducing dataset specificity for deepfakes using ensemble learning
6. Multi-branch deepfake detection algorithm based on fine-grained features
7. Deepfake videos detection based on texture features
8. A deepfake detection algorithm based on fourier transform of biological signal
9. F2Trans: High-frequency fine-grained transformer for face forgery detection10.1109/TIFS.2022.3233774 ↗
10. FInfer: Frame inference-based deepfake detection for high-visual-quality videos
11. Leveraging real talking faces via self-supervision for robust forgery detection
12. FAMM: Facial muscle motions for detecting compressed deepfake videos over social networks10.1109/TCSVT.2023.3278310 ↗
13. MRE-Net: Multi-rate excitation network for deepfake video detection10.1109/TCSVT.2023.3239607 ↗
14. MSVT: Multiple spatiotemporal views transformer for deepfake video detection10.1109/TCSVT.2023.3281448 ↗
15. Deepfake video detection via facial action dependencies estimation
16. Self-supervised video forensics by audio-visual anomaly detection
17. Dynamic difference learning with spatio-temporal correlation for deepfake video detection10.1109/TIFS.2023.3290752 ↗
18. Jointly defending deepfake manipulation and adversarial attack using decoy mechanism10.1109/TPAMI.2023.3253390 ↗
19. Towards understanding the generalization of deepfake detectors from a game-theoretical view
20. Restricted black-box adversarial attack against deepfake face swapping10.1109/TIFS.2023.3266702 ↗
21. G. Pei et al., “Deepfake generation and detection: A benchmark and survey,” 2024, arXiv:2403.17881.
22. Detecting deepfake videos using digital watermarking
23. A system for mitigating the problem of deepfake news videos using watermarking10.2352/ISSN.2470-1173.2020.4.MWSF-117 ↗
24. AI-assisted deepfake detection using adaptive blind image watermarking10.1016/j.jvcir.2024.104094 ↗
25. Auto-Encoding VariationalBayes
26. Neural discrete representation learning
27. Generative adversarial networks10.1145/3422622 ↗
28. Analyzing and improving the image quality of stylegan
29. High-resolution image synthesis with latent diffusion models
30. DiT-Head: High resolution talking head synthesis using diffusion transformers
31. A style-based generator architecture for generative adversarial networks
32. SimSwap: An efficient framework for high fidelity face swapping
33. BlendFace: Re-designing identity encoders for face-swapping
34. DiffSwap: High-fidelity and controllable face swapping via 3D-aware masked diffusion
35. IA-FaceS: A bidirectional method for semantic face editing10.1016/j.neunet.2022.11.016 ↗
36. DPE: Disentanglement of pose and expression for general video portrait editing
37. TransEditor: Transformer-based dual-space gan for highly controllable facial editing
38. FENeRF: Face editing in neural radiance fields
39. Dual-generator face reenactment
40. Real-time expression transfer for facial reenactment10.1145/2816795.2818056 ↗
41. Face2Face: Real-time face capture and reenactment of rgb videos
42. A. Radford, “Unsupervised representation learning with deep convolutional generative adversarial networks,” 2015, arXiv:1511.06434.
43. Wasserstein gan
44. An image Turing test on realistic gastroscopy images generated by using the progressive growing of generative adversarial networks10.1007/s10278-023-00803-2 ↗
45. Stgan: A unified selective transfer network for arbitrary image attribute editing
46. A hybrid cybersecurity algorithm for digital image transmission over advanced communication channel models
47. Reversible watermarking method with low distortion for the secure transmission of medical images
48. Invariant image watermarking based on statistical features in the low-frequency domain10.1109/TCSVT.2008.918843 ↗
49. An intelligent sensor data preprocessing method for oct fundus image watermarking using an rcnn
50. Combinational image watermarking in the spatial and frequency domains10.1016/S0031-3203(02)00122-X ↗
51. J. Zhu, R. Kaplan, J. Johnson, and F. Li, “HiDDeN: Hiding data with deep networks,” 2018, arXiv:1807.09937.10.1007/978-3-030-01267-0_40 ↗
52. MBRS: Enhancing robustness of DNN-based watermarking by mini-batch of real and simulated jpeg compression
53. Fragile watermarking tamper detection via bilinear fuzzy relation equations10.1007/s12652-018-0806-3 ↗
54. Proactive image manipulation detection via deep semi-fragile watermark10.1016/j.neucom.2024.127593 ↗
55. Efficient image tampering localization using semi-fragile watermarking and error control codes10.1016/j.sigpro.2021.108342 ↗
56. StegaStamp: Invisible hyperlinks in physical photographs
57. The stable signature: Rooting watermarks in latent diffusion models
58. Evading watermark based detection of AI-generated content
59. Artificial fingerprinting for generative models: Rooting deepfake attribution in training data
60. Responsible disclosure of generative models using scalable fingerprinting
61. C. Kim, Y. Ren, and Y. Yang, “Decentralized attribution of generative models,” 2021, arXiv:2010.13974.
62. Enhancing the robustness of deep learning based fingerprinting to improve deepfake attribution
63. Faketagger: Robust safeguards against deepfake dissemination via provenance tracking
64. Faketracer: Exposing deepfakes with training data contamination
65. Proactive deepfake defence via identity watermarking
66. Source-ID-Tracker: Source face identity protection in face swapping
67. Hiding face into background: A proactive countermeasure against malicious face swapping10.1109/TII.2024.3396268 ↗
68. T. Wang, M. Huang, H. Cheng, B. Ma, and Y. Wang, “Robust identity perceptual watermark against deepfake face swapping,” 2024, arXiv:2311.01357.
69. Dual defense: Adversarial, traceable, and invisible robust watermarking against face swapping10.1109/TIFS.2024.3383648 ↗
70. Are watermarks bugs for deepfake detectors? rethinking proactive forensics
71. Y. Yang, C. Liang, H. Hè, X. Cao, and N. Z. Gong, “FaceGuard: Proactive deepfake detection,” 2021, arXiv:2109.05673.
72. FaceSigns: Semi-fragile watermarks for media authentication10.1145/3640466 ↗
73. WaterLo: Protect images from deepfakes using localized semi-fragile watermark
74. BiFPro: A bidirectional facial-data protection framework against deepfake
75. SepMark: Deep separable watermarking for unified source tracing and deepfake detection
76. EditGuard: Versatile image watermarking for tamper localization and copyright protection
77. Image quality assessment: From error visibility to structural similarity10.1109/TIP.2003.819861 ↗
78. The unreasonable effectiveness of deep features as a perceptual metric
79. Gans trained by a two time-scale update rule converge to a local nash equilibrium
80. G. B. Huang, M. A. Mattar, T. L. Berg, and E. Learned-Miller, “Labeled faces in the wild: A database for studying face recognition in unconstrained environments,” in Workshop on Faces in “Real-Life” Images: Detection, Alignment, and Recognition, 2008.
81. D. Yi, Z. Lei, S. Liao, and S. Li, “Learning face representation from scratch,” 2014, arXiv:1411.7923.
82. Deep learning face attributes in the wild
83. Progressive growing of gans for improved quality, stability, and variation
84. VGGFace2: A dataset for recognising faces across pose and age
85. Maskgan: Towards diverse and interactive facial image manipulation
86. FaceForensics++: Learning to detect manipulated facial images
87. Celeb-DF: A large-scale challenging dataset for deepfake forensics