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{181016,
        author = {Yatheendra K V and Dr. Sudhakara Arabagatte},
        title = {Performance Evaluation of AI-Enhanced Detection Methods for Image-Based and Alphanumeric Substitution Plagiarism Manipulations},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {12},
        number = {1},
        pages = {3515-3519},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=181016},
        abstract = {The sophistication of plagiarism techniques continues to evolve, making detection increasingly challenging. Among the most evasive manipulations are embedding text as images and performing alphanumeric substitutions that evade conventional text-matching algorithms. This paper presents a multi-layered AI-enhanced detection system that combines OCR-based extraction, proportionating algorithms, advanced regular expressions, and language model-assisted validation. Evaluated on a real-world dataset of 5000 academic reports, the proposed system achieved an accuracy of 85%, significantly improving upon the baseline accuracy of 55%. The results demonstrate the system's robustness in handling advanced manipulation tactics while also highlighting the continuous need for adaptive model improvements},
        keywords = {plagiarism detection, AI, OCR, alphanumeric substitution, proportionating algorithm, academic integrity, experimental results.},
        month = {June},
        }