• Geetika Nag
• Lavanya Pathak
• Mahak Agarwal

Code plagiarism has become a serious issue in academics and software development, with students and programmers frequently copying or modifying existing code to bypass detection. Traditional plagiarism detection tools rely mainly on text-based comparison, making them ineffective when users rename variables, alter code structure, or translate code between programming languages. This project introduces an AI-powered Code Plagiarism Detection System that enhances accuracy by analyzing the logical structure of code rather than just its text. By leveraging deep learning, Abstract Syntax Trees (AST), and Control Flow Graphs (CFG), the system can detect similarities even when code is heavily modified. Unlike conventional tools, it provides users write code, scans external sources such as GitHub and Stack Overflow, and offers interactive reports with highlighted matching sections. Additionally, it ensures data security and privacy through encryption. With its advanced AI-driven approach, this system offers a smarter and more reliable way to detect plagiarism, making it highly valuable for educational institutions, competitive programming platforms, and software companies to maintain originality and integrity in coding.

Code Plagiarism, AST, CFG

"Unraveling AI-Based Plagiarism Across Programming Paradigms", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.12, Issue 7, page no.b683-b691, July-2025, Available :http://www.jetir.org/papers/JETIR2507179.pdf

"Unraveling AI-Based Plagiarism Across Programming Paradigms", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.12, Issue 7, page no. ppb683-b691, July-2025, Available at : http://www.jetir.org/papers/JETIR2507179.pdf