HISPI Project Cerebellum HISPI PROJECT CEREBELLUM

Preprints Reportedly from Researchers from Multiple Universities Allegedly Contain Covert AI Prompts

July 1, 2025

17 academic preprints on arXiv, reportedly from researchers across multiple universities, allegedly contained covert prompts instructing AI tools to deliver only positive peer reviews. These lead authors are affiliated with institutions in eight countries including Waseda University, KAIST, Peking University, and the University of Washington. The concealed instructions, some embedded using white text or tiny fonts, were intended to influence any reviewers who rely on AI tools for decision-making.

This incident underscores the need for safe and secure AI practices. For those interested in shaping governance around AI and preventing such incidents, consider joining Project Cerebellum by visiting JOIN US.
The HISPI Project Cerebellum TAIM aims to Measure and Map such occurrences to promote harm prevention and guardrails for AI.

Matched TAIM controls

Suggested mapping from embedding similarity (not a formal assessment). Browse all TAIM controls

Alleged deployer
unnamed-peer-reviewers, unnamed-conference-paper-reviewers
Alleged developer
unnamed-large-language-model-developers
Alleged harmed parties
peer-review-process, academic-integrity, academic-conferences, research-community

Source

Data from the AI Incident Database (AIID). Cite this incident: https://incidentdatabase.ai/cite/1135

Data source

Incident data is from the AI Incident Database (AIID).

When citing the database as a whole, please use:

McGregor, S. (2021) Preventing Repeated Real World AI Failures by Cataloging Incidents: The AI Incident Database. In Proceedings of the Thirty-Third Annual Conference on Innovative Applications of Artificial Intelligence (IAAI-21). Virtual Conference.

Pre-print on arXiv · Database snapshots & citation guide

We use weekly snapshots of the AIID for stable reference. For the official suggested citation of a specific incident, use the “Cite this incident” link on each incident page.