• Prof Kanchan Warke
• Dhanshri Gurule
• Shruti Nahar
• Unnati Jadhav
• Prachi Wadhavane

In recent months, free deep learning-based software tools have made it easier to produce convincing face-to-face interactions in films with little sign of editing in the so-called "DeepFake" (DF) videos. Visual effects have effectively demonstrated the manipulation of digital videos for many years, but new developments in deep learning have dramatically improved the realism of fake content and the ease with which it may be produced. These allegedly AI-generated media (popularly referred to as DF). The challenge of creating the DF with artificial intelligence techniques is straightforward. However, it is a significant challenge to find these DF .Due to the complexity of training the algorithm to detect the DF .We've moved ahead a little bit With the use of convolutional neural networks and recurrent neural networks, we have made progress in detecting the DF Network. Convolutional neural networks (CNN) are used by the system to extract features at the frame level. These characteristics are utilised to train a recurrent neural network (RNN) that can identify whether or not a video has undergone alteration and can identify the temporal irregularities between frames brought about by the DF generation tools. Expected outcome when compared to a sizable collection of phoney videos obtained from a standard data source. We demonstrate how our system's ability to perform well on this task while utilising a straightforward design. Keywords: Deepfake Video Detection, convolutional Neural network (CNN), recurrent neural network (RNN).

LSTM CNN

"Deepfake Detection through deep learning ", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.10, Issue 5, page no.n328-n337, May-2023, Available :http://www.jetir.org/papers/JETIR2305D50.pdf

"Deepfake Detection through deep learning ", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.10, Issue 5, page no. ppn328-n337, May-2023, Available at : http://www.jetir.org/papers/JETIR2305D50.pdf