Abstract
Fake digital content disseminated over the internet has been posing a great challenge for the various social media platforms and real-world applications. The technological advancement has facilitated the generation of such content, such that differentiating between fake and factual content has become ever more challenging. One such emerging technology, known as deepfake, can create some new hyper-realistic but fraudlent material that cannot be easily captured by human eyes and seems utmost realistic. The technology relies on AI and its subsets, namely machine learning, and deep learning. It is pertinent to note that the research in this direction is meager and there is an instant need for novel approaches that can reliably discriminate between genuine and fake multimedia content. The current paper aims to review the deepfake technology along with its associated threats, challenges, and future directions that can help cope with fake information circulated online. The accuracy and robustness of available methods for detecting such fake videos based on the available two generations of datasets are deliberated. Constructive criticism is presented that also highlights some of its useful applications for the digital society.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
S. Lyu, Deepfake detection: Current challenges and next steps. IEEE International Conference on Multimedia & Expo Workshops (ICMEW), London, United Kingdom., pp. 1–6 (2020).https://doi.org/10.1109/ICMEW46912.2020.9105991
L. Yuezun, L. Siwei,Exposing deepfake videos by detecting face warping artifacts. IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) (2019)
A. Hauser, M. Ruef (eds.), Deepfake—An introduction. https://www.scip.ch/en/?labs.20181004
X. Yang, Y. Li, S. Lyu, Exposing deep fakes using inconsistent head poses. IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP) (2019)
W. Mika,The emergence of deepfake technology: A review. Technol. Innov. Manag. Rev. 9, 39–52 https://doi.org/10.22215/timreview/1282. (2019)
I. Goodfellow, J. Pouget-Abadie, M. Mirza, B. Xu, D. W. Farley, S. Ozair, A. Courville, Y. Bengio, Generative adversarial nets. Advances in Neural Information Processing Systems (NIPS), pp. 2672–2680 (2014)
D. Guera, E.J. Delp, Deepfake video detection using recurrent neural networks. AVSS(2018)
M. Masood, M. Nawaz, K. Malik, A. Javed, A. Irtaza, Deepfakes Generation and Detection: State-of-the-art, open challenges, countermeasures, and way forward (2021) https://arxiv.org/abs/2103.00484
T. Ruben, S.R. Tapiador, J. Fierrez, R. Vera-Rodriguez, Deep-fakes evolution: Analysis of facial regions and fake detection performance. In Biometrics and data pattern analytics—BiDA Lab, Universidad Autonoma de Madrid (2020) arXiv:2004.07532
L. Yuezun, M.-C. Chang, S. Lyu, In ictu oculi: Exposing AI generated fake facevideos by detecting eye blinking. IEEE International Workshop on Information Forensics and Security (WIFS) (2018)
T. Karras, T. Aila, S. Laine, J. Lehtinen, Progressive growing of gans for improved quality, stability, and variation. The International Conference on Learning Representations (ICLR) (2017)
Y. Choi, M. Choi, M. Kim, J.W. Ha, S. Kim, J. Choo, Stargan: Unified generative adversarial networks for multi-domain image-to-image translation. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 8789–8797 (2018)
F. Matern, C. Riess, M. Stamminger, Exploiting visual artifacts to expose deep-fakes and face manipulations. IEEE Winter Applications of Computer Vision Workshops (WACVW) (2019)
D. Afchar, V. Nozick, J. Yamagishi, I. Echizen, Mesonet: a compact facial video forgery detection network. IEEE International Workshop on Information Forensics and Security (WIFS) (2018)
B. Dolhansky, R. Howes, B. Pflaum, N. Baram, C. Ferrer, The deepfake detection challenge (DFDC) preview dataset. arXiv:1910.08854 (2019)
R. Durall, M. Keuper, F. Pfreundt, J. Keuper, Unmasking deepfakes with simple Features. Retrieved 17 April 2021, from (2021) https://arxiv.org/abs/1911.00686
H.R. Hasan, K. Salah, Combating deepfake videos using blockchain and smart contracts. IEEE Access(2019)
L. Haodong, L. Bin, T. Shunquan, H. Jiwu, Detection of deep network generated images using disparities in color components (2018). arXiv:1808.07276
I. Amerini,L. Galteri, R. Caldelli, A. Del Bimbo, Deepfake video detection through optical flow based CNN. IEEE/CVF International Conference on Computer Vision Workshop (ICCVW), Seoul, Korea (South) (2019), pp. 1205–1207. https://doi.org/10.1109/ICCVW.2019.00152
T.T. Nguyen, C.M. Nguyen, T. Nguyen, T. Nguyen, S. Nahavandi, Deep learning for deepfakes creation and detection (2019). arXiv:1909.11573
E. Sabir, J. Cheng, A. Jaiswal, W. AbdAlmageed, I. Masi, P. Natarajan, Recurrent convolutional strategies for face manipulation detection in videos. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops (2019), pp. 80–87
M. Kaur, S. Gupta, A passive blind approach for image splicing detection based on DWT and LBP histograms. International Symposium on Security in Computing and Communication (2016), pp. 318–327. https://doi.org/10.1007/978-981-10-2738-3_27
M. Kaur, S. Gupta, A fusion framework based on fuzzy integrals for passive-blind image tamper detection. Cluster Computing 22.https://doi.org/10.1007/s10586-017-1393-3 (2019)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Sharma, M., Kaur, M. (2022). A Review of Deepfake Technology: An Emerging AI Threat. In: Ranganathan, G., Fernando, X., Shi, F., El Allioui, Y. (eds) Soft Computing for Security Applications . Advances in Intelligent Systems and Computing, vol 1397. Springer, Singapore. https://doi.org/10.1007/978-981-16-5301-8_44
Download citation
DOI: https://doi.org/10.1007/978-981-16-5301-8_44
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-16-5300-1
Online ISBN: 978-981-16-5301-8
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)