An efficient deepfake video detection using robust deep learning

Abstract

The creation and manipulation of synthetic images have evolved rapidly, causing serious concerns about their effects on society. Although there have been various attempts to identify deep fake videos, these approaches are not universal. Identifying these misleading deepfakes is the first step in preventing them from spreading on social media sites. We introduce a unique deep-learning technique to identify fraudulent clips. Most deepfake identifiers currently focus on identifying face exchange, lip synchronous, expression modification, puppeteers, and other factors. However, exploring a consistent basis for all forms of fake videos and images in real-time forensics is challenging. We propose a hybrid technique that takes input from videos of successive targeted frames, then feeds these frames to the ResNet-Swish-BiLSTM, an optimized convolutional BiLSTM-based residual network for training and classification. This proposed method helps identify artifacts in deepfake images that do not seem real. To assess the robustness of our proposed model, we used the open deepfake detection challenge dataset (DFDC) and Face Forensics deepfake collections (FF++). We achieved 96.23% accuracy when using the FF++ digital record. In contrast, we attained 78.33% accuracy using the aggregated records from FF++ and DFDC. We performed extensive experiments and believe that our proposed method provides more significant results than existing techniques.

Keywords

• Video deepfakes
• Multimedia forensics
• Swish
• Visual manipulation