Key points are not available for this paper at this time.
As a result of AI's rapid development in recent years, a wide range of tools and methods for editing multimedia have found widespread use. When technology was readily available, it was often misused or exploited illegally instead of being put to good use in areas such as entertainment and education. The term "deep fake" was used relatively recently to characterize digitally altered films and photos that pass muster as legitimate and high-quality productions. The literature review led to the discovery of multiple methods for detecting deep fakes. It is crucial to work on improving fraud detection systems and expanding video and audio forensics studies. In this article, we take a closer look at some of the various deep fake creation and detection algorithms now under study like Xception Network, Long Short Term Memory (LSTM), Convolutional Neural Networks (CNN), Recurrent Neural Networks (RNN). The detection of deep fake system will be served using by these techniques. We also used a standardized way to compare various approaches.
Chauhan et al. (Thu,) studied this question.