Integrity Shield A System for Ethical AI Use & Authorship Transparency in Assessments
On the map: LLM safety and security → Watermarking generated content and models
Abstract (arXiv)
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.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Watermarking generated content and models, one of 12 directions in LLM safety and security. Builds on 7 of its 16 references that are in the map. First posted on arXiv 16 Jan 2026.
Builds on
7 of 16 references.
References · 7
- 2024Gemini 1.5: Unlocking multimodal understanding across millions of tokens of contextcited by 3,224
- 2023DetectGPT: Zero-Shot Machine-Generated Text Detection using Probability Curvaturecited by 726
- 2022ChatGPT: The End of Online Exam Integrity?cited by 88
- 2024Technical Report on the Pangram AI-Generated Text Classifiercited by 34
- 2025EditLens: Quantifying the Extent of AI Editing in Textcited by 26
- 2024Keystroke Dynamics Against Academic Dishonesty in the Age of LLMscited by 6
- 2025TRAPDOC: Deceiving LLM Users by Injecting Imperceptible Phantom Tokens into Documentscited by 6
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2026DoPE: Decoy Oriented Perturbation Encapsulation Human-Readable, AI-Hostile Documents for Academic Integrity
- 2025In-Context Watermarks for Large Language Models
- 2024ModelShield: Adaptive and Robust Watermark against Model Extraction Attack
- 2025Watermarking Large Language Models in Europe: Interpreting the AI Act in Light of Technology
- 2024PostMark: A Robust Blackbox Watermark for Large Language Models
- 2024Can Watermarking Large Language Models Prevent Copyrighted Text Generation and Hide Training Data?
- 2024SHIELD: Evaluation and Defense Strategies for Copyright Compliance in LLM Text Generation
- 2025Unified attacks to large language model watermarks: spoofing and scrubbing in unauthorized knowledge distillation