Authors : Dr. Anant N. Kaulage; Pranjali Kolawale; Anika Tuli; Isha Liddad; Tanvi Jadhav

Volume/Issue : Volume 11 - 2026, Issue 4 - April

Google Scholar : https://tinyurl.com/epdc8yfp

Scribd : https://tinyurl.com/4w7p48jr

DOI : https://doi.org/10.38124/ijisrt/26apr2035

Note : A published paper may take 4-5 working days from the publication date to appear in PlumX Metrics, Semantic Scholar, and ResearchGate.

Abstract : Deepfake technology, driven by modern AI models, has made video manipulation more convincing and harder to detect. This project aims to develop a deep learning based system that can automatically identify whether a video is real or artificially generated. The approach uses the EfficientNetB0 architecture as a feature extractor, trained on frames extracted from both authentic and manipulated video datasets. Frames were preprocessed, resized, and augmented to enhance the model’s learning ability to learn the given pattern. The training process involved two stages: initial training of top layers and subsequent fine-tuning of the entire network for higher accuracy. Further refinement was done using real video samples to enhance prediction stability. A threshold calibration method was applied to decide the real or fake nature of videos based on average prediction scores across frames. The final model efficiently distinguishes between real and fake content, demonstrating strong performance and potential use in video authenticity verification.

Keywords : Convolutional Neural Network, Deepfake, Fine Tuning.

References :

1. Karen Simonyan and Andrew Zisserman, “Very Deep Convolutional Networks for Large–Scale Image Recognition”, ICLR 2015, arXiv:1409.1556v6 [cs.CV], 10 Apr 2015.
2. Chesney, Robert and Citron, Danielle Keats, Deep Fakes: A Looming Challenge for Privacy, Democracy, and National Security (July 14, 2018). 107 California Law Review (2019, Forthcoming); U of Texas Law, Public Law Research Paper No. 692; U of Maryland Legal Studies Research Paper No. 2018-21.
3. Yuezun Li, Ming-Ching Chang and Siwei Lyu, In Ictu Oculi: Exposing AI Generated Fake Face Videos by Detecting Eye Blinking, arXiv:1806.02877v2 [cs.CV], 11 Jun 2018.
4. Yuezun Li and Siwei Lyu, “Exposing DeepFake Videos By Detecting Face Warping Artifacts”, arXiv:1811.00656v3 [cs.CV], 22 May 2019.
   https://doi.org/10.1016/S0969-4765(19)30137-7
5. Darius Afchar, Vincent Nozick, Junichi Yamagishi and Isao Echizen, “MesoNet: A Compact Facial Video Forgery Detection Network”, arXiv:1809.00888v1 [cs.CV], 4 Sep 2018.
   https://doi.org/10.1109/WIFS.2018.8630761
6. Xin Yang, Yuezun Li and Siwei Lyu, “Exposing Deep Fakes Using Inconsistent Head Poses”, ICASSP 2019 - 2019 IEEE ICASSP, 17 May 2019.
7. Huy H. Nguyen, Junichi Yamagishi, and Isao Echizen, “Use of a Capsule Network to Detect Fake Images and Videos”, arXiv:1910.12467v2 [cs.CV], 29 Oct 2019.
8. Falko Matern, Christian Riess and Marc Stamminger, “Exploiting Visual Artifacts to Expose Deepfakes and Face Manipulations”, 2019 IEEE Winter Applications of Computer Vision Workshops (WACVW).
   https://doi.org/10.1109/WACVW.2019.00020
9. Jessica and Silbey Woodrow Hartzog, “The Upside of Deep Fakes”, Maryland Law Review, Volume 78, Issue 4, 2019.
10. Schwartz, Oscar (12 November 2018). "You thought fake news was bad? Deep fakes are where the truth goes to die". The Guardian.
11. Sik-Ho Tsang, “Review: Inception-v3 — 1st Runner Up (Image Classification) in ILSVRC 2015”, https://medium.com/@sh.tsang/review-inception-v3-1st-runner-up-image-classification-in-ilsvrc-2015-17915421f77c
12. Pavel Korshunov, Sebastien Marcel, “DeepFakes: A New Threat to Face Recognition? Assessment and Detection”, citing arXiv:1812.08685 [cs.CV], 20 Dec 2018.
13. David Güera, Edward J. Delp, “Deepfake Video Detection Using Recurrent Neural Networks”, 2018 15th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS).
    https://doi.org/10.1109/AVSS.2018.8639163
14. Brian Dolhansky, Russ Howes, Ben Pflaum, Nicole Baram, Cristian Canton Ferrer, “The Deepfake Detection Challenge (DFDC) Preview Dataset”, arXiv:1910.08854 [cs.CV], 19 Oct 2019.
15. Pavel Korshunov and Sebastien Marcel, “Vulnerability Assessment and Detection of Deepfake Videos”, IAPR International Conference, 2019.
16. Thanh Thi Nguyen, Cuong M. Nguyen, Dung Tien Nguyen, Duc Thanh Nguyen, Saeid Nahavandi, “Deep Learning for Deepfakes Creation and Detection”, arXiv:1909.11573 [cs.CV], 25 Sep 2019.
17. Ekraam Sabir, Jiaxin Cheng, Ayush Jaiswal, Wael AbdAlmageed, Iacopo Masi, Prem Natarajan, “Recurrent Convolutional Strategies for Face Manipulation Detection in Videos”, arXiv:1905.00582 [cs.CV], 2 May 2019.
18. Shuo Yuan, Xinguo Yu, Abdul Majid, “Robust Face Tracking Using Siamese-VGG with Pre-training and Fine-tuning”, 4th International Conference on Control and Robotics Engineering (ICCRE), 20–23 April 2019.
    https://doi.org/10.1109/ICCRE.2019.8724212
19. Francesco Marra, Diego Gragnaniello, Davide Cozzolino, Luisa Verdoliva, “Detection of GAN-Generated Fake Images over Social Networks”, IEEE Conference on Multimedia Information Processing and Retrieval (MIPR), 10–12 April 2018.
20. Shubhangi Tirpude, Naman Vidyabhanu, Hashir Sheikh, Shoeb Pathan, Zeeshan Ali Syed, Shivam Singh, “Abnormal X-Ray Detection System using Convolution Neural Network”, International Journal of Advanced Trends in Computer Science and Engineering, ISSN 2278-3091, Volume 9, No. 1, January–February 2020.