为考试文档加防抄袭水印，阻止AI代考并追踪答题来源
Integrity Shield A System for Ethical AI Use & Authorship Transparency in Assessments
- 在试卷文件层嵌入不可见水印，不改变外观却能识别
- 对4种商用大模型实现91%-94%的答题阻断率
- 可追溯每道题的答案归属，适合教师和考试机构使用
大型语言模型（LLMs）如今可直接解析上传的考试PDF并完成整套试题，严重威胁学术诚信与成绩可信度。现有水印技术或作用于词元层面，或需控制模型解码过程，在学生使用外部黑箱系统时失效。我们提出Integrity Shield——一种文档层水印系统，可在保持试卷人眼可见性不变的前提下，嵌入具有结构感知能力、针对每道题的水印。这些水印能有效阻止多模态大模型回答受保护的试卷，并在模型或学生作答中稳定恢复题级签名。在涵盖理工、人文与医学推理的30份试卷上，该系统对四种商业大模型实现91%-94%的考试级阻断率，且签名恢复率达89%-93%。演示系统支持教师上传试卷、预览水印效果，并查看前后AI表现及作者身份证据。
原文摘要 · Abstract (English)
Large Language Models (LLMs) can now solve entire exams directly from uploaded PDF assessments, raising urgent concerns about academic integrity and the reliability of grades and credentials. Existing watermarking techniques either operate at the token level or assume control over the model's decoding process, making them ineffective when students query proprietary black-box systems with instructor-provided documents. We present Integrity Shield, a document-layer watermarking system that embeds schema-aware, item-level watermarks into assessment PDFs while keeping their human-visible appearance unchanged. These watermarks consistently prevent MLLMs from answering shielded exam PDFs and encode stable, item-level signatures that can be reliably recovered from model or student responses. Across 30 exams spanning STEM, humanities, and medical reasoning, Integrity Shield achieves exceptionally high prevention (91-94% exam-level blocking) and strong detection reliability (89-93% signature retrieval) across four commercial MLLMs. Our demo showcases an interactive interface where instructors upload an exam, preview watermark behavior, and inspect pre/post AI performance & authorship evidence.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。