DeepFake Detection using LSTM and ResNeXt CNN

**Problem:** Deepfakes are being used for malicious purposes such as spreading fake news, blackmail, identity theft, reputation damage, etc., hence, its detection is crucial for companies to easily detect fraud and protect themselves from unprecedented damage to their brand reputation, customer data and financial loss.

**Solution:** Deepfake Detection in videos using Deep Learning techniques like ResNeXt and LSTM

**Approach:** This project would detect deepfakes used in videos using deep learning techniques like ResNeXt and LSTM. We would perform transfer learning where the pre-trained ResNeXt CNN would be used to obtain a feature vector, further the LSTM layer would be trained using the features.
Then we would make a Django application where a user can upload the video and submit that to the model for prediction. The trained model performs the prediction and the result is displayed on the screen.

**Importance:** While there are several advantages, yet deepfakes can be used for malicious purposes such as spreading fake news, blackmail, and identity theft. Secondly, deepfakes can have serious consequences for individuals and organisations, including damage to reputation and financial loss. Deepfake detection is crucial for maintaining the integrity of news and information, ensuring that what people see and hear is accurate and trustworthy.