Abstract
New computing methods and digital content have been created thanks to recent advancements in digital media technology. They have also contributed to advancing recent AI-based innovations and provide straightforward instruments for producing real video changes. These "Deep Fakes" or fraudulent films might seriously jeopardise the public’s perceptions of a case or society. These films’ consequences on spreading fake news, particularly, are significant when they act as accurate depictions. These false films may, however, be created by manipulating software. Data protection, identifying deep fakes, and preventing media manipulation are just a few ways deep fake detection contributes to cybersecurity. In light of this, it is essential and mandatory to be able to spot this sort of misleading data. This paper examines the most promising new approaches to deep fake video detection by analysing the latest findings from the research community. It analysed the results from two research and proposed using convolutional neural networks and long short-term memory to distinguish fake from real video frames. The report suggested using these and other detection methods and the unique method for identifying deep fakes that used the YOLO face detector to distinguish facial video frames (YOLO-CNN-XGBoost) and suggested investigating other novel detection methods.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.