Automated Detection of AI-Obfuscated Plagiarism in Modeling Assignments
Plagiarism is a widespread problem in computer science education, aggravated by the impracticability of manual inspection and the low risk of detection in large courses. Even worse, tools based on large language models like ChatGPT have made it easier than ever to obfuscate plagiarized solutions. Additionally, most plagiarism detectors only apply to code, and only a few approaches exist for modeling assignments, which lack broad resilience to obfuscation attacks. This paper presents a novel approach for automated plagiarism detection in modeling assignments that combines automated analysis with human inspection. We evaluate our approach with real-world assignments and plagiarism obfuscated by ChatGPT. Our results show that we achieve a significantly higher detection rate for AI-generated attacks and a broader resilience than the state-of-the-art.
More on JPlag:
Fri 19 AprDisplayed time zone: Lisbon change
14:00 - 15:30 | LLM, NN and other AI technologies 6Software Engineering Education and Training / Research Track / Software Engineering in Practice at Grande Auditório Chair(s): Bowen Xu North Carolina State University | ||
14:00 15mTalk | Make LLM a Testing Expert: Bringing Human-like Interaction to Mobile GUI Testing via Functionality-aware Decisions Research Track Zhe Liu Institute of Software, Chinese Academy of Sciences, Chunyang Chen Technical University of Munich (TUM), Junjie Wang Institute of Software, Chinese Academy of Sciences, Mengzhuo Chen Institute of Software, Chinese Academy of Sciences, Boyu Wu University of Chinese Academy of Sciences, Beijing, China, Xing Che Institute of Software, Chinese Academy of Sciences, Dandan Wang Institute of Software, Chinese Academy of Sciences, Qing Wang Institute of Software, Chinese Academy of Sciences | ||
14:15 15mTalk | Automated Detection of AI-Obfuscated Plagiarism in Modeling Assignments Software Engineering Education and Training Timur Sağlam Karlsruhe Institute of Technology (KIT), Sebastian Hahner Karlsruhe Institute of Technology (KIT), Larissa Schmid Karlsruhe Institute of Technology, Erik Burger Karlsruhe Institute of Technology (KIT) DOI Pre-print | ||
14:30 15mTalk | AI-Tutoring in Software Engineering Education Software Engineering Education and Training Eduard Frankford University of Innsbruck, Clemens Sauerwein University of Innsbruck, Patrick Bassner Technical University of Munich, Stephan Krusche Technical University of Munich, Ruth Breu University of Innsbruck DOI Pre-print | ||
14:45 15mTalk | Beyond Functional Correctness: An Exploratory Study on the Time Efficiency of Programming Assignments Software Engineering Education and Training Yida Tao Southern University of Science and Technology, Wenyan Chen Southern University of Science and Technology, Qingyang Ye Southern University of Science and Technology, Yao Zhao Southern University of Science and Technology | ||
15:00 15mTalk | Does ChatGPT Help With Introductory Programming?An Experiment of Students Using ChatGPT in CS1 Software Engineering Education and Training Yuankai Xue Vanderbilt University, Hanlin Chen Vanderbilt University, Gina Bai North Carolina State University, Robert Tairas Vanderbilt University, Yu Huang Vanderbilt University | ||
15:15 15mTalk | A New Frontier of AI: On-Device AI Training and Personalization Software Engineering in Practice Jijoong Moon Samsung Electronics, Hyun Suk Lee Samsung Electronics, Jiho Chu Samsung Electronics, Donghak Park Samsung Electronics, Seungbaek Hong Samsung Electronics, Hyungjun Seo Samsung Electronics, Donghyeon Jeong Samsung Electronics, Sungsik Kong Samsung Electronics, MyungJoo Ham Samsung Electronics Pre-print | ||