1.Athul Sathyapal (STM17CS011)

2.Fabina AT (STM17CS012)

3.Muhammed Jasil U (STM17CS018)

4.Shabna NP (STM17CS024)

In recent years, a machine learning based free software tool has made it easy to create believable face swaps in videos that leaves few traces of manipulation, in what are known as “ deep fake “ videos. Scenarios where these realistic fake videos are used to create political distress, blackmail someone or fake terrorism events are easily envisioned. In this project we propose a new approach to detect deepfakes generated through the generative adversarial network (GANs) model via an algorithm called Deep Vision to analyze a significant change in the pattern of blinking. Human eye blinking pattern has been known to significantly change according to the person’s overall physical conditions, cognitive activities, biological factors and information processing level.The proposed method called DeepVision is implemented as a measure to verify an anomaly based on the period, repeated number,and elapsed eye blink time when eye blinks were continuously repeated within a very short period of time. Our system uses a convolutional neural network (CNN) to extract framelevel features. These features are then used to train a recurrent neural network(RNN) that learns to classify if a a video has been subjected to manipulation or not.The proposed system also recognize the deepfake images that can be generated through widespread mobile apps like FACEAPP.