Deepfake Video Detection Using Recurrent Neural Networks

TLDR

Recent machine‑learning tools enable creation of realistic face‑swap videos with minimal traces, raising concerns about political manipulation, blackmail, and fake terrorism. The study proposes a temporal‑aware pipeline for automatic deepfake video detection. The pipeline extracts frame‑level features with a CNN, feeds them to an RNN that classifies manipulation, and is evaluated on a large, multi‑website deepfake dataset. The system achieves competitive detection performance with a simple architecture.

Abstract

In recent months 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 "deepfake" videos. Scenarios where these realistic fake videos are used to create political distress, blackmail someone or fake terrorism events are easily envisioned. This paper proposes a temporal-aware pipeline to automatically detect deepfake videos. Our system uses a convolutional neural network (CNN) to extract frame-level features. These features are then used to train a recurrent neural network (RNN) that learns to classify if a video has been subject to manipulation or not. We evaluate our method against a large set of deepfake videos collected from multiple video websites. We show how our system can achieve competitive results in this task while using a simple architecture.