Enhancing Deepfake Detection Through Hybrid MobileNet-LSTM Model with Real-Time Image and Video Analysis
V S Anandhasivam, A K Anusri, M Logeshwar, Reetha Gopinath · 2024
The race to crush information integrity and public trust is being won by one thing: deepfakes, AI manipulated media. The goal is to enhance the Deepfake detection using MobileNet V3 and LSTM network. MobileNet's lightweight CNN architecture is able to induce the visual features in an image by an image and in a video and can pick up the slight visual clues of textures and facial structure. Some temporal inconsistencies that cannot be seen by image base methods are then analyzed using an LSTM network. The hybrid model is trained on real and deepfake media datasets, and is thus adaptable to emerging deepfake techniques. This has a user face interface to analyze the real time and fly media to get the analysis and analysis score and visual feedback of the identified artifacts. Unique to this system is its versatility for images and videos, and its real time capability, making it a suitable choice for practical use in social media, journalism, and law enforcement combating the spread of misinformation with a guarantee of digital media authenticity