Copyright © 2025 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{169123,
        author = {Gaurav Singh Bisht and Pratik Bhavsing Gavit and Arnav Ashish Godhamgaonkar and Poshiya Harshil Himatbhai and Prof. J. S. Pawar},
        title = {Theoretical Idea On Using GAN Discriminator To Detect Visual Data Generated Using GAN},
        journal = {International Journal of Innovative Research in Technology},
        year = {2024},
        volume = {11},
        number = {6},
        pages = {352-358},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=169123},
        abstract = {With the rise in digital content generation, deep fake images have become a growing concern, posing threats to privacy, security, and credibility. This paper introduces a study on deep fake image detection tool based on Generative Adversarial Networks (GAN), which aims to differentiate authentic images from those synthetically generated. By leveraging deep learning, specifically the discriminator of a GAN framework, the system identifies inconsistencies in deep fake images, providing reliable detection for use in various fields such as media verification, cybersecurity, and legal applications.
Our system employs a generator-discriminator architecture, where the discriminator is trained to recognize fake images generated by the generator, improving its ability to spot telltale signs of deep fakes. Trained on extensive datasets of both real and fake images, this model is able to learn subtle differences and accurately flag synthetic content. The goal of this tool is to enhance the detection of manipulated images, aiding sectors that require image authenticity verification.},
        keywords = {Deep fake Detection, Deep Fake , Adversarial Networks , Machine Learning , Generative Adversarial Networks(GAN)},
        month = {November},
        }