DEEPFAKE DILEMMA: A REVIEW STUDY ON VIDEO SYNTHESIS TECHNOLOGY

Akshat Kedawat; Aloke Das

doi:10.29121/shodhkosh.v5.iICETDA24.2024.2033

Authors

Akshat Kedawat Student, Animation & VFX Department, Poornima University, Jaipur, Rajasthan.
Dr. Aloke Das Associate Professor, Animation & VFX Department, Poornima University, Jaipur, Rajasthan

DOI:

https://doi.org/10.29121/shodhkosh.v5.iICETDA24.2024.2033

Keywords:

Deepfake, Face Swapping, Video Synthesis, Detection, Ethics, Artificial Intelligence, Misinformation

Abstract [English]

This review paper provides information of deepfake video technology, a rapidly evolving dimension of artificial intelligence with profound implication for media, privacy & Society.
Exploring the fundamental methods used to create deepfakes, this paper explores the advancements in machine leaning, particularly focusing on Generative Adversarial Networks (GAN)s & Neural Architecture Network responsible for hyper-realistic synthesis of facial expression, gestures and voices.
An important part of the investigation is devoted to ethical questions, asking whether deepfake technology might be used as a weapon to spread misinformation, steal identities, or invade privacy.
The impact on Society as a whole is highlighted in the report, along with the necessity for preventative actions to lessons the negative consequences of malicious deepfake distribution & the decline in public confidence in digital media
The review addresses the persistent challenges of detecting deepfake content, closely examine methodologies from traditional forensics to innovate machine leaning based approaches
Highlighting the Cat & mouse game between creators & Detectors, the paper discusses the limitations of existing detection methods & the urgent requirements for more advanced & expandable solution.

References

Chesney, B., Citron, D.: Deep fakes: a looming challenge for privacy, democracy, and national security. Calif. L. Rev. 107, 1753 (2019) DOI: https://doi.org/10.2139/ssrn.3213954

Dixon, H.B., Jr.: Deepfakes: More frightening than photoshop on steroids. Judges J. 58(3), 35–37 (2019

Neekhara, P., et al.: Adversarial deepfakes: Evaluating vulnerability of deepfake detectors to adversarial examples. arXiv preprint arXiv:2002.12749. (2020)

Thies, J., et al.: Face2face: real-time face capture and reenactment of RGB videos. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2387–2395 (2016) DOI: https://doi.org/10.1109/CVPR.2016.262

Kim, H., et al.: Deep video portraits. ACM Trans. Graph. 37(4), 1–14 (2018) DOI: https://doi.org/10.1145/3197517.3201283

Zhou, P., et al.: Two-stream neural networks for tampered face detection. 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) (2017) DOI: https://doi.org/10.1109/CVPRW.2017.229

Dolhansky, B., et al.: The deepfake detection challenge (DFDC) preview dataset. arXiv preprint arXiv:1910.08854. (2019)

Amerini, I., et al.: Deepfake video detection through optical flow-based CNN. Proceedings of the IEEE International Conference on Computer Vision Workshops (2019) DOI: https://doi.org/10.1109/ICCVW.2019.00152

Li, Y., Lyu, S.: Exposing deepfake videos by detecting face warping artifacts. arXiv preprint arXiv:1811.00656. (2018)

Dang, H., et al.: On the detection of digital face manipulation. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern recognition, pp. 5781–5790 (2020). DOI: https://doi.org/10.1109/CVPR42600.2020.00582

Güera, D., Edward, J.: Delp: Deepfake video detection using recurrent neural networks. In: 2018 15th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS), pp. 1–6. IEEE (2018) DOI: https://doi.org/10.1109/AVSS.2018.8639163

Zhao, Y., et al.: Capturing the persistence of facial expression features for deepfake video detection. In: International Conference on Information and Communications Security, pp. 630–645.Springer (2019) DOI: https://doi.org/10.1007/978-3-030-41579-2_37

Z. Lu, Z. Li, J. Cao, R. He, and Z. Sun. Recent progress of face image synthesis. arXiv:1706.04717, June 2017. DOI: https://doi.org/10.1109/ACPR.2017.2

Dufour, N., Gully, A.: Deepfakes Detection Dataset (2019)

Carlini, N., Farid, H.: Evading deepfake-image detectors with white-and black-box attacks. arXiv preprint arXiv:2004.00622. (2020) DOI: https://doi.org/10.1109/CVPRW50498.2020.00337