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{199819,
        author = {Yuvraj Singh Pawar and Rushikesh Agarwal and Soham Dahatonde and Dr. Anant Kaulage},
        title = {Deepfake AI Detection System Using ML},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {11},
        pages = {13322-13325},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=199819},
        abstract = {The increasing number of AI-generated contents raises questions related to the veracity of the information provided by it and the overall trust of people. With the development of modern deepfakes technology, it becomes possible to create highly realistic images that become almost impossible to identify as synthetic. In this paper, we propose a machine learning approach for detecting AI-generated images through a deep convolutional neural network model. Our model is designed as an EfficientNet-B0 structure that was initially pretrained on ImageNet and then fine-tuned for binary classification of images into two classes: authentic images and synthetic. The algorithm utilizes additional heuristic approaches for increasing robustness, such as frequency domain analysis with the use of FFT transform, as well as statistical analysis. The whole project was developed and presented using a FastAPI backend with a web interface for image uploads and realtime processing. Combining deep learning algorithms with auxiliary techniques and providing a convenient web platform allows us to develop an efficient and practical approach towards detection of deepfakes images.},
        keywords = {Deepfake Detection, EfficientNet, Machine Learning, AI-Generated Images, Image Classification, Computer Vision},
        month = {April},
        }