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{193297,
        author = {Samarth Tambe and Chetan Gajula and Raj Kubal and Harsh Hanchate and Archana Gopnarayan},
        title = {A Survey on Deep Learning Techniques for Deepfake Image/Video Detection},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {9},
        pages = {4650-4656},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=193297},
        abstract = {Deepfakes are synthetically generated media created using advanced deep learning techniques that manipulate a person’s facial appearance or speech to produce highly realistic forged content. The rapid advancement of generative models has raised serious concerns regarding digital media authenticity, making reliable detection mechanisms essential. This paper presents a deep learning-based framework for image and video level deepfake detection, focusing on identifying spatial manipulation artifacts in facial regions.
The proposed system follows a structured processing pipeline that includes dataset collection, preprocessing, facial frame extraction, and feature analysis using convolutional neural network architectures. Pretrained models such as XceptionNet, MesoNet, and Efficient-Net are integrated to extract discriminative spatial features indicative of forgery. These architectures were selected to maintain a practical balance between detection performance and computational efficiency. The current implementation includes model integration and preprocessing modules, with ongoing work dedi-cated to fine-tuning, evaluation, and improving robust-ness under compressed and real-world conditions. The framework aims to provide an accurate, scalable, and practically deployable solution for deepfake detection.},
        keywords = {Deepfake Detection, Deep Learning, Video Analysis, Neural Networks, Digital Forensics},
        month = {February},
        }