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{174676,
        author = {Shivansh Pathak and Bijendra Tyagi and Lekhansh Sachan and Shyam Singh},
        title = {Truescan : Deepfake Detection System},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {11},
        number = {11},
        pages = {790-796},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=174676},
        abstract = {The rapid advancement of generative models has led to the emergence of highly sophisticated face manipulation techniques, such as DeepFakes and Face2Face, which pose significant risks, including misinformation, privacy violations, and security threats. As manipulated media becomes more convincing, the need for robust deepfake detection methods has grown. Early detection techniques primarily focused on frame-based analysis, but they struggled with temporal coherence, leading to the development of video-based approaches incorporating deep learning models like CNNs, LSTMs, and multimodal detection frameworks. This paper reviews the latest advancements in deepfake detection, analyzing the strengths and limitations of various methods, including quantum transfer learning, adversarial robustness techniques, and multimodal data integration. We also propose TrueScan, a hybrid detection pipeline that leverages dynamic temporal modeling, adversarial robustness, and efficient neural architectures to improve detection accuracy and scalability. TrueScan aims to set a new benchmark in real-time deepfake detection by addressing computational efficiency and generalization challenges. Finally, we discuss implementation challenges, future research directions, and the potential for adaptive, scalable solutions to counter evolving deepfake threats effectively.},
        keywords = {Deepfake detection, adversarial attacks, convolutional neural networks, deep learning models, media forensics, model robustness,},
        month = {March},
        }