РОЗРОБКА МОДЕЛІ ВИЯВЛЕННЯ ФЕЙКОВОГО КОНТЕНТУ НА ОСНОВІ АРХІТЕКТУРИ EFFICIENTNET

The research is devoted to efficiency evaluation of modern deepfake detection models based on convolutional neural networks (CNN). In today's world, with the growing influence of digital technology and increasing volume of information on the internet, detection of fake images and videos has become increasingly important. Fake content spread through social media and other platforms can cause serious damage, from personal attacks to manipulation of public opinion on a global level. During the study, we trained a model based on the EfficientNet architecture. The model was trained on the Deepfake Detection Challenge dataset