CASEBOOK

Browse / Indirect Prompt Injection / AIID-1135

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

AIID-1135 ยท 2025-07-01 real-world incident

Class
Indirect Prompt Injection (filed by a model that read the source)
Technique
Real-world incidents
Affected
Large Language Model Developers (incident)

What happened, in short

Researchers reportedly hid prompts in arXiv preprints, using white or tiny text, instructing AI tools to give only positive peer reviews to any reviewer relying on AI. (Our summary, written by a model. The source text is below.)

Details

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.

References

Source: AI Incident Database, used under CC BY-SA 4.0.