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{205188,
        author = {Vrushali Gawai and Gajanan Arsalwad and Sanika Deshmukh and Trupti Dhandar},
        title = {AI Academic plagiarism checker with code analysis and multilingual model},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {13},
        number = {1},
        pages = {6773-6779},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=205188},
        abstract = {While AI-generated text and global digital availability have revolutionized content creation, they have simultaneously escalated the complexity of academic plagiarism. Traditional lexical matching methods are increasingly obsolete against sophisticated paraphrasing, cross-lingual translation, and AI-synthetic code. This paper presents SmartPlag, an advanced multi-modal framework designed to transcend simple word-by-word matching. SmartPlag integrates a multi-stage pipeline comprising real-time language detection, concurrent pivot-language translation, and TF-IDF semantic vectorization to identify cross-lingual plagiarism. Uniquely, the system introduces a Cognitive Effort Imbalance (CEI) behavioural analysis module and Stylometric Machine Learning classification to distinguish between organic human logic and automated generation in programming source code. By analysing entropy in naming conventions and variance in structural complexity, SmartPlag provides a "cognitive footprint" of submissions. Experimental results demonstrate high efficacy in detecting direct, translated, and AI-assisted plagiarism, offering a scalable and intelligent solution for preserving academic integrity in the era of generative AI.},
        keywords = {},
        month = {June},
        }