Comparative analysis of deepfake detection methods using machine learning and deep learning
Poorva Agrawal, Soham Pathak, Shruti Potey, Vaishnavi Dhengre, Nitin Rakesh, R. Parvathi · 2024
The paper examines the growing issue of deepfake technology, which uses cutting-edge machine learning to spoof face features in videos. This technology has the potential to be abused in a number of situations, including blackmail, political manipulation, and the staging of terrorist acts. The study’s main goal is to present a thorough summary of current studies that use cutting-edge deep learning techniques to identify fake information. The Deepfakes Detection Challenge (DFDC) dataset is introduced, neural network applications are covered, and the effectiveness of current deepfake detection models is assessed. Because deepfake applications potentially pose a hazard, the research emphasizes the need for tools that can automatically detect and evaluate the integrity of digital visual data. Additionally, it discusses numerous algorithms and approaches that have been put out in the literature for producing and identifying deepfakes, with a focus on deep learning-based methods.