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{180645,
        author = {Prof. Shah Saloni Niranjan and Dhole Priyanka and Lambote Maya and Naikwade Arti},
        title = {Deepfake Detection System Using Machine Learning},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {12},
        number = {1},
        pages = {1649-1653},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=180645},
        abstract = {The rise of DeepFake technology has raised significant concerns about the authenticity of digital media, particularly in areas such as security, politics, and entertainment. This research addresses the problem of detecting DeepFake faces in images and videos, which have become increasingly sophisticated and harder to distinguish from real human faces. The primary research question explored in this study is: How can machine learning and image processing techniques be utilized to effectively detect DeepFake faces?To tackle this problem, a combination of machine learning algorithms and advanced image processing techniques was employed. The methodology involves training convolutional neural networks (CNNs) on a dataset containing both real and DeepFake images. Image preprocessing steps, such as face alignment, normalization, and enhancement, were used to optimize the input data for the model. Various machine learning models were tested, including deep learningbased approaches, to assess their accuracy in detecting manipulated faces.The results show that the CNN-based model achieved an accuracy rate of [insert specific accuracy], significantly outperforming traditional image processing methods. The study also identified key features that distinguish real faces from DeepFakes, such as subtle inconsistencies in facial textures, eye blinking, and lighting artifacts.The significance of this research lies in its potential to enhance the detection of DeepFake faces in real-world applications. This study contributes to the ongoing effort to combat the malicious use of synthetic media by providing a more reliable and automated detection method. Furthermore, the results can be applied to improve digital forensics, security protocols, and social media platforms' efforts to prevent the spread of misinformation. Moreover, it enhances security by minimizing the chances of identity theft and impersonation. To evaluate the effectiveness of the system, a comprehensive dataset containing images and videos of various individuals is collected and used for training and testing the machine learning models. The system is benchmarked against existing authentication methods to assess its accuracy, efficiency, and robustness. The experimental results demonstrate the superiority of the proposed approach in terms of accuracy and security.},
        keywords = {Data Collection and Dataset, Face Detection, Image Processing Techniques, Machine Learning Models,Feature Extraction, Model Training and Evaluation, Model Optimization and Fine-tuning, PostProcessing, Deployment.},
        month = {June},
        }