LLMMedium
Preprints Reportedly from Researchers from Multiple Universities Allegedly Contain Covert AI Prompts
- Occurred
- Jul 1, 2025
- Published
- Jul 1, 2025
- Source
- AI Incident Database
Summary
Hidden prompts reportedly were discovered in at least 17 academic preprints on arXiv that purportedly instructed AI tools to deliver only positive peer reviews. The lead authors are reportedly affiliated with 14 institutions in eight countries, including Waseda University, KAIST, Peking University, and the University of Washington. The alleged concealed instructions, some of which were reportedly embedded using white text or tiny fonts, were purportedly intended to influence any reviewers who rely on AI tools.
Developers
- Large language model developers
Deployers
- Unnamed peer reviewers
- Unnamed conference paper reviewers
Harmed parties
- Peer review process
- Academic integrity
- Academic conferences
- Research community
Tags
- Peer review
- Peer review manipulation
- Hidden prompts
- Academic integrity
- Prompt injection
- AI-assisted review
- Publication ethics
- Preprint
- Preprint platforms
- Research misconduct
Classification
Category confidence: 90%
Severity confidence: 85%
Rationale: Incident involves covert AI prompts in academic preprints to manipulate peer review, representing an LLM misuse failure.
Classifier: Qwen/Qwen3.5-35B-A3B-FP8