Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{193928,
        author = {Mano Ranjan K S and Jothy N and Nithish Benadict S N and Nithishwara V and Ramani M},
        title = {Deepfake Face Detection Using Deep Learning},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {10},
        pages = {1961-1965},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=193928},
        abstract = {Deepfake images are a big problem for keeping things secure online because they can make fake pictures look totally real. It’s kind of scary how they manipulate visuals so easily. In this project, I tried building a detection system based on deep learning, using something called ResNet architecture. The idea was to use transfer learning to pull out key features from faces and then decide if an image is real or not. I think that helps because ResNet is already trained on a lot of stuff, so it adapts quicker. For the data, I split it into parts for training, checking during the process, and final testing. Preprocessing involved making all images the same size and normalizing them, which I guess is necessary to avoid weird biases. Training happened with the Adam optimizer, and I looked at accuracy along with a few other metrics to see how it performed. The results came out to about 81 percent accuracy, which shows ResNet can handle deepfake detection okay, even if its not perfect yet. Some cases might still slip through, it seems.},
        keywords = {DeepFake Detection, Convolutional Neural Networks (CNN), RESNET, Deep Learning, Generative Adversarial Networks (GAN).},
        month = {March},
        }