Abstract:

Deepfakes are synthetic media in which a person in an existing image or video is replaced with someone else’s likeness. Generative Adversarial Networks, or GANs, are a deep-learningbased generative model. More generally, GANs are a model architecture for training a generative model, and it is most common to use deep learning models in this architecture. In the case of GANs, the generator model applies meaning to points in a chosen latent space, such that new points drawn from the latent space can be provided to the generator model as input and used to generate new and different output examples.. Thus we can easily use GANs to create deepfakes which can then be misused in a number of places. Deepfakes are concerning everyone out there in the digital world. The project deals with detection of deepfakes using Renext and LSTMs and packages the benefits of deep learning to detect deepfakes in the form of a Django web Application, To detect deepfakes we gather the frames from the video uploaded and split the video into desired number of frames. Following that we make use of python face recognition libraries and other C++ visual libraries to detect the face of the character from the video. We then apply our models ,which are trained for different number of frame sequences to predict if the video is a deepfake or Real.

Description:

Deep learning, Res-Next Convolution Neural Network, Long short-term memory, Face Recognition, PyTorch