• Aarsh Rajesh Vanjare

In recent months, free deep learning-based software tools have facilitated the creation of highly realistic face exchanges in videos, commonly referred to as "DeepFake" (DF) videos. While digital video manipulation has existed for decades through advanced visual effects, recent advancements in deep learning have drastically improved the realism and accessibility of AI-synthesized media. Creating DFs using artificial intelligence (AI) tools has become relatively simple, but detecting them remains a significant challenge due to the complexity of training algorithms to identify synthetic content. Our research focuses on a novel approach to DF detection using a combination of Convolutional Neural Networks (CNN) and Recurrent Neural Networks (RNN). The system utilizes a CNN to extract frame-level features, which are then analyzed by an RNN to detect temporal inconsistencies introduced during DF creation. Our model has been tested against a large dataset of fake videos and has shown promising results, achieving high accuracy with a simple yet effective architecture.

"Deepfake detection and enhancement using deep learning", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.12, Issue 3, page no.i387-i393, March-2025, Available :http://www.jetir.org/papers/JETIR2503855.pdf

"Deepfake detection and enhancement using deep learning", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.12, Issue 3, page no. ppi387-i393, March-2025, Available at : http://www.jetir.org/papers/JETIR2503855.pdf