Abstract
In the age of technologies, a brand-new technology in the field of deep neural networks and artificial intelligence has been developed. This technology of creating counter-fit realistic videos is known as Deepfake and is born lately. It's troublesome to discriminate between fake and real videos which are daily uploaded on the web across different websites. There are several Deepfake open-source creation methods available online, which results in a growing number of fake videos on the web. There are many quick and efficient ways and techniques which are made to spot, observe, and detect these developments. To define a few, comparison of backgrounds, facial artifacts, blinking of eyes, pattern analysis, pose, and likewise features of the face and surroundings are used to help in detecting a Deepfake video. In this paper, a simple but effective approach for detecting fakes using 2D Convolutional Neural Network (Conv2D) is followed and the use of 3D Convolutional Neural Network (Conv3D) is introduced in Deepfake Detection with the addition of Multi-Task Cascade Convolutional Neural Network (MTCNN) in preprocessing. The significance and importance of this work are that a different approach is taken in preprocessing which in return gives better results and the introduction for the use of Conv3D. The proposed models are trained and tested on celeb-df v2 and Deepfake-TIMIT both low-quality (LQ) and high-quality videos (HQ) with gaining the highest accuracy of 99.81%. Also, compared to the state-of-the-art techniques, the proposed approach helped in gaining a good accuracy on low-quality videos, and the difference between both HQ and LQ is observed to be less than 1%.
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
Afchar D, Nozick V, Yamagishi J, Echizen I (2018) MesoNet: a compact facial video forgery detection network. In: 2018 IEEE international workshop on information forensics and security (WIFS), Hong Kong, Hong Kong, pp 1–7.https://doi.org/10.1109/WIFS.2018.8630761
Li Y, Chang M, Lyu S (2018) In ictu oculi: exposing AI created fake videos by detecting eye blinking. In: 2018 IEEE international workshop on information forensics and security (WIFS), Hong Kong, Hong Kong, pp 1–7.https://doi.org/10.1109/WIFS.2018.8630787
Güera D, Delp EJ (2018) Deepfake video detection using recurrent neural networks. In: 2018 15th IEEE international conference on advanced video and signal based surveillance (AVSS), Auckland, New Zealand, pp 1–6. https://doi.org/10.1109/AVSS.2018.8639163
Yang X, Li Y, Lyu S (2019) Exposing deep fakes using inconsistent head poses. In: ICASSP 2019–2019 IEEE international conference on acoustics, speech and signal processing (ICASSP), Brighton, United Kingdom, pp 8261–8265. https://doi.org/10.1109/ICASSP.2019.8683164
Amerini I, Galteri L, Caldelli R, Del Bimbo A (2019) Deepfake video detection through optical flow based CNN. In: 2019 IEEE/CVF international conference on computer vision workshop (ICCVW), Seoul, Korea (South), pp 1205–1207. https://doi.org/10.1109/ICCVW.2019.00152
Kharbat FF, Elamsy T, Mahmoud A, Abdullah R (2019) Image feature detectors for deepfake video detection. In: 2019 IEEE/ACS 16th international conference on computer systems and applications (AICCSA), Abu Dhabi, United Arab Emirates, pp 1–4. https://doi.org/10.1109/AICCSA47632.2019.9035360
Wu X, Xie Z, Gao Y, Xiao Y (2020) SSTNet: detecting manipulated faces through spatial, steganalysis and temporal features. In: ICASSP 2020–2020 IEEE international conference on acoustics, speech and signal processing (ICASSP), Barcelona, Spain, pp 2952–2956. https://doi.org/10.1109/ICASSP40776.2020.9053969
Jung T, Kim S, Kim K (2020) DeepVision: deepfakes detection using human eye blinking pattern. IEEE Access 8:83144–83154. https://doi.org/10.1109/ACCESS.2020.2988660
Jafar MT, Ababneh M, Al-Zoube M, Elhassan A (2020) Forensics and analysis of deepfake videos. In: 2020 11th international conference on information and communication systems (ICICS), Irbid, Jordan, pp 053–058. https://doi.org/10.1109/ICICS49469.2020.239493
Younus MA, Hasan TM (2020) Effective and fast deepfake detection method based on haar wavelet transform. In: 2020 International conference on computer science and software engineering (CSASE), Duhok, Iraq, pp 186–190. https://doi.org/10.1109/CSASE48920.2020.9142077
Tursman E, George M, Kamara S, Tompkin J (2020) Towards untrusted social video verification to combat deepfakes via face geometry consistency. In: 2020 IEEE/CVF conference on computer vision and pattern recognition workshops (CVPRW), Seattle, WA, USA, pp 2784–2793. https://doi.org/10.1109/CVPRW50498.2020.00335
Fernandes S et al (2020) Detecting deepfake videos using attribution-based confidence metric. In: 2020 IEEE/CVF conference on computer vision and pattern recognition workshops (CVPRW), Seattle, WA, USA, pp 1250–1259. https://doi.org/10.1109/CVPRW50498.2020.00162
Yuezun L, Lyu S (2019) Exposing deepfake videos by detecting face warping artifacts. CVPR workshops
Nguyen HH et al (2019) Capsule-forensics: using capsule networks to detect forged images and videos. In: ICASSP 2019–2019 IEEE international conference on acoustics, speech and signal processing (ICASSP), pp 2307–2311
Nguyen HH, Yamagishi J, Echizen I (2019) Use of a capsule network to detect fake images and videos. (Cornell University). arXiv:1910.12467
Durall R, Keuper M, Pfreundt F, Keuper J (2019) Unmasking deepfakes with simple features. (Cornell University). arXiv:1911.00686.
Jeon H, Bang Y, Woo SS (2020) FDFtNet: facing off fake images using fake detection fine-tuning network. (Cornell University). arXiv:2001.01265
Bonettini N, Cannas ED, Mandelli S, Bondi L, Bestagini P, Tubaro S (2020) Video face manipulation detection through ensemble of CNNs. (Cornell University). arXiv:2004.07676
Bonomi M, Pasquini C, Boato G (2020) Dynamic texture analysis for detecting fake faces in video sequences. (Cornell University). arXiv:2007.15271
Pishori A, Rollins B, Houten NV, Chatwani N, Uraimov O (2020) Detecting deepfake videos: an analysis of three techniques. (Cornell University). arXiv:2007.08517
Zhang X, Karaman S, Chang S (2019) Detecting and simulating artifacts in GAN fake images. In: 2019 IEEE international workshop on information forensics and security (WIFS). pp 1–6. https://doi.org/10.1109/WIFS47025.2019.9035107
Li Y, Yang X, Sun P, Qi H, Lyu S (2020) Celeb-DF: a large-scale challenging dataset for deepfake forensics. In: 2020 IEEE/CVF conference on computer vision and pattern recognition (CVPR), pp 3204–3213.https://doi.org/10.1109/CVPR42600.2020.00327
Korshunov P, Marcel S Deepfakes: a new threat to face recognition? assessment and detection. Link to download: https://zenodo.org/record/4068245#.YOwvfegzbIU
Sanderson C, Lovell BC (2009) Multi-region probabilistic histograms for robust and scalable identity inference. Lecture notes in computer science (LNCS), vol 5558, pp 199–208. Link to download: https://conradsanderson.id.au/vidtimit/#downloads
Matern F, Riess C, Stamminger M (2019) Exploiting visual artifacts to expose deepfakes and face manipulations. In: Proceedings of the IEEE winter applications of computer vision workshops
Zhou P, Han X, Morariu X, Davis L (2017) Two-stream neural networks for tampered face detection. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition workshops
Nguyen H, Fang F, Yamagishi J, Echizen I (2019) Multi-task learning for detecting and segmenting manipulated facial images and videos. arXiv:1906.06876
Suratkar S, Kazi F, Sakhalkar M, Abhyankar N, Kshirsagar M (2020) Exposing deepfakes using convolutional neural networks and transfer learning approaches. In: 2020 IEEE 17th India council international conference (INDICON), pp 1–8. https://doi.org/10.1109/INDICON49873.2020.9342252
Suratkar S, Johnson E, Variyambat K, Panchal M, Kazi F (2020) Employing transfer-learning based CNN architectures to enhance the generalizability of deepfake detection. In: 2020 11th international conference on computing, communication and networking technologies (ICCCNT), pp 1–9. https://doi.org/10.1109/ICCCNT49239.2020.9225400
Acknowledgements
The authors are thankful to the CoE-CNDS lab, VJTI Mumbai, for providing them DGX-1 to train the models and obtain the results on the test dataset.
Author information
Authors and Affiliations
Corresponding author
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
Suratkar, S., Sharma, P. (2022). A Simple and Effective Way to Detect DeepFakes: Using 2D and 3D CNN. In: Rao, U.P., Patel, S.J., Raj, P., Visconti, A. (eds) Security, Privacy and Data Analytics. Lecture Notes in Electrical Engineering, vol 848. Springer, Singapore. https://doi.org/10.1007/978-981-16-9089-1_19
Download citation
DOI: https://doi.org/10.1007/978-981-16-9089-1_19
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-16-9088-4
Online ISBN: 978-981-16-9089-1
eBook Packages: Computer ScienceComputer Science (R0)