A Survey of Available Techniques for The Deepfake Detection Using the Deep Learning Technique Based on Gan
Keywords:
Digital Smart Devices, Smartphones, Tablets, Laptops, Digital Cameras, Multimedia MaterialAbstract
The proliferation of affordable digital smart devices such as smartphones, tablets, laptops, and digital cameras has led to a rapid increase of multimedia material (such as photographs and movies) on the internet. Furthermore, the progression of social media in the last decade has facilitated the fast sharing of multimedia material, resulting in a substantial rise in the creation of multimedia content and its accessibility. Simultaneously, we have seen significant progress in the area of machine learning with the implementation of advanced algorithms capable of effortlessly manipulating multimedia material to disseminate false information on social media platforms. Due to the proliferation of misleading information and its rapid dissemination, it has become more difficult to ascertain the truth and have confidence in the accuracy of information, leading to potentially detrimental outcomes. Furthermore, in the present day, we are seeing a period known as the “post-truth” age, in which malicious individuals use both accurate and false information to sway the views of the general public. Disinformation is a deliberate tactic that may have serious consequences, such as manipulating elections, inciting conflict, and defaming individuals. Recently, there has been substantial progress in the development of deepfake technology, which has the potential to spread misinformation worldwide and might represent a serious danger in the future by creating fake news. Deepfakes refer to artificially created videos and sounds using AI technology. Currently, the use of films as evidence is standard practice in all areas of civil and criminal justice procedures. In order for a video to be accepted as evidence, it must be shown to be genuine and its integrity must be confirmed. However, the majority of current multimedia forensic examiners encounter the difficulty of interpreting multimedia files obtained from social networks and sharing websites such as YouTube and Facebook, as potential evidence. Meeting the need for authenticity and integrity while identifying altered films on social media is a formidable undertaking, particularly as the sophistication of deepfake creation increases. After the deepfakes have been made, the use of potent, advanced, and user-friendly alteration tools (such as Zao[1], REFACE[2], FaceApp[3], Audacity [4], Soundforge [5]) might complicate the process of authenticating and verifying the integrity of the created movies.
Downloads
References
ZAO, Available at: https://apps.apple.com/cn/app/zao/id1465199127. Accessed: September 09, 2020.
Reface App, Available at: https://reface.app/. Accessed: September 11, 2020.
FaceApp, Available at: https://www.faceapp.com/. Accessed: September 17, 2020.
Audacity, Available at: https://www.audacityteam.org/. Accessed: September 09, 2020.
Sound Forge, Available at: https://www.magix.com/gb/music/sound-forge/. Accessed: January 11, 2021.
J. F. Boylan, “Will deep-fake technology destroy democracy?,” The New York Times, Oct, vol. 17, 2018.
C. Chan, S. Ginosar, T. Zhou, and A. A. Efros, “Everybody Dance Now,” in Proceedings of the IEEE International Conference on Computer Vision, 2019, pp. 5933-5942.
K. M. Malik, H. Malik, and R. Baumann, “Towards vulnerability analysis of voice-driven interfaces and countermeasures for replay attacks,” in 2019 IEEE Conference on Multimedia Information Processing and Retrieval (MIPR), 2019, pp. 523-528: IEEE.
K. M. Malik, A. Javed, H. Malik, and A. Irtaza, “A light-weight replay detection framework for voice controlled iot devices,” IEEE Journal of Selected Topics in Signal Processing, vol. 14, no. 5, pp. 982-996, 2020.
A. Javed, K. M. Malik, A. Irtaza, and H. Malik, “Towards protecting cyber-physical and IoT systems from single-and multi-order voice spoofing attacks,” Applied Acoustics, vol. 183, p. 108283, 2021.
M. Aljasem et al., “Secure Automatic Speaker Verification (SASV) System through sm-ALTP Features and Asymmetric Bagging,” IEEE Transactions on Information Forensics Security, 2021.
L. Verdoliva, “Media forensics and deepfakes: an overview,” arXiv preprint arXiv:2001.06564,
R. Tolosana, R. Vera-Rodriguez, J. Fierrez, A. Morales, and J. Ortega-Garcia, “Deepfakes and beyond: A survey of face manipulation and fake detection,” arXiv preprint arXiv:2001.00179, 2020.
T. T. Nguyen, C. M. Nguyen, D. T. Nguyen, D. T. Nguyen, and S. Nahavandi, “Deep Learning for Deepfakes Creation and Detection,” arXiv preprint arXiv:1909.11573, 2019.
Downloads
Published
Issue
Section
License
Copyright (c) 2024 International Journal of Scientific Research in Science and Technology
![Creative Commons License](http://i.creativecommons.org/l/by/4.0/88x31.png)
This work is licensed under a Creative Commons Attribution 4.0 International License.