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{209569,
        author = {Shahu Nikam and Swarup Bonde and Shreya Bhavsar and Shravani Kawade and Prof. R. V. Shinde},
        title = {DeltaDetect AI-Powered Plagiarism Detection and Automated Report Generation},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {13},
        number = {5},
        pages = {2530-2534},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=209569},
        abstract = {Academic plagiarism has become harder to detect because paraphrasing tools and generative AI systems such as ChatGPT and Gemini can produce text that keyword-matching checkers do not recognize, while capable commercial tools are costly and need documents to be uploaded to external servers. This paper presents DeltaDetect, a proposed AI-powered plagiarism detection system that combines TF-IDF keyword vectorization with Sentence-BERT (SBERT) semantic embeddings in a weighted hybrid similarity score, and adds a self-trained offline classifier for AI-generated content that needs no third-party API. The findings are compiled automatically into a PDF report with a similarity percentage, an AI-content score, highlighted passages and matched sources. The paper describes the architecture, modules, working principle and planned evaluation of the system, which is intended to give institutions a private, free-to-use and explainable originality-verification tool.},
        keywords = {Plagiarism Detection, TF-IDF, Sentence-BERT, Semantic Similarity, AI-Generated Content Detection, Report Generation},
        month = {October},
        }